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

    Neuronpedia

    INDEX
    Explanations

    articles and determiners in sentences

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

    German articles and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ooster
    -0.51
     bénévoles
    -0.48
     énergétique
    -0.47
    väg
    -0.46
     vectorielle
    -0.45
    Volunteers
    -0.45
     ajutor
    -0.45
     bénévol
    -0.44
     kupić
    -0.44
     enää
    -0.44
    POSITIVE LOGITS
     Das
    0.62
     das
    0.59
    ')))
    0.59
    }])
    0.57
    $")
    0.56
    )))))
    0.55
    })),
    0.53
    Das
    0.52
     DAS
    0.52
    ")));
    0.51
    Act Density 0.002%

    No Known Activations