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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate challenges and perseverance in professional settings

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

    Attribution or speech reporting

    np_acts-logits-general · gemini-2.0-flash

    attribution for speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    })*/
    -0.58
     Please
    -0.56
    MLLoader
    -0.55
     Our
    -0.55
    Resumo
    -0.55
     please
    -0.54
     hereby
    -0.53
    Erreferentziak
    -0.51
     my
    -0.49
     thereto
    -0.49
    POSITIVE LOGITS
    Says
    1.21
     Says
    1.07
    says
    1.01
     says
    0.98
     Explains
    0.95
    Asked
    0.90
    Adds
    0.90
     Adds
    0.89
     Asked
    0.85
     ifølge
    0.84
    Act Density 0.171%

    No Known Activations