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

    Neuronpedia

    INDEX
    Explanations

    starting or following specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    1.06
    >();
    0.90
    ,
    0.90
    \
    0.90
     the
    0.89
    ?
    0.88
     elic
    0.86
    fontawesome
    0.85
    อาจ
    0.82
    '];
    0.81
    POSITIVE LOGITS
    們
    1.00
    s
    0.88
    salt
    0.86
    skeleton
    0.82
    ﺳ
    0.82
    ों
    0.81
    İN
    0.81
     DEI
    0.80
     Đấy
    0.80
    iß
    0.80
    Act Density 0.000%

    No Known Activations