Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to the status of objects or conditions, particularly focusing on the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "not," "was," "were," or "is"

    np_acts-logits-general · gemini-2.0-flash

    is/was/were followed by adjective/participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abbraccio
    -0.57
     gracia
    -0.52
     testemun
    -0.50
     الاطلاع
    -0.50
     coloro
    -0.49
     execução
    -0.47
     asemenea
    -0.47
     lievito
    -0.47
     reprend
    -0.46
     metastasis
    -0.46
    POSITIVE LOGITS
    ніципалі
    0.87
    Personensuche
    0.77
    }))
    0.71
     smaller
    0.69
    SharedDtor
    0.69
     Audiodateien
    0.68
     manufactured
    0.66
     चीज़ों
    0.65
     taller
    0.65
     labeled
    0.65
    Act Density 0.467%

    No Known Activations