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

    Neuronpedia

    INDEX
    Explanations

    cities and their locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ુ
    0.87
     RenderTexture
    0.75
    p
    0.75
    ু
    0.75
    キ
    0.75
    ൈ
    0.74
    ！”
    0.72
    تب
    0.71
     Avrupa
    0.71
    타
    0.71
    POSITIVE LOGITS
    ,
    1.09
    ↵↵
    0.99
    .
    0.96
    ?
    0.89
    ה
    0.83
    '
    0.83
    ying
    0.81
     prudent
    0.75
    ας
    0.73
    iasi
    0.72
    Act Density 0.003%

    No Known Activations