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

    Neuronpedia

    INDEX
    Explanations

    comment section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     documentation
    0.64
    documentation
    0.60
     documentación
    0.58
    Documentation
    0.54
     dokument
    0.54
     Documentation
    0.53
     Dokument
    0.53
    explanatory
    0.53
    説明
    0.52
     erklärt
    0.52
    POSITIVE LOGITS
     Comment
    1.30
     comment
    1.29
    Comment
    1.29
     댓글
    1.15
    评论
    1.13
     commenter
    1.10
    댓글
    1.10
    comment
    1.06
     comentario
    1.01
     коммента
    0.99
    Act Density 0.022%

    No Known Activations