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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Member
    -0.08
    -Ta
    -0.07
    ُن
    -0.07
     millenn
    -0.06
     feat
    -0.06
     Commentary
    -0.06
     Ago
    -0.06
    卷
    -0.06
    mmas
    -0.06
     yatır
    -0.06
    POSITIVE LOGITS
     совершенно
    0.07
    -↵↵
    0.07
     emotionally
    0.06
     وهو
    0.06
     sincerely
    0.06
    dirname
    0.06
    statusCode
    0.06
    030
    0.06
     од
    0.06
    55
    0.06
    Act Density 0.004%

    No Known Activations