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

    Neuronpedia

    INDEX
    Explanations

    sibling relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ă
    0.94
    ৭
    0.87
     I
    0.86
     Então
    0.81
    ăm
    0.80
    āl
    0.80
    ée
    0.80
    あ
    0.77
     அது
    0.77
    ā
    0.77
    POSITIVE LOGITS
    <0x0D>
    1.16
    ج
    1.14
    ث
    1.14
    ים
    1.10
    ش
    1.09
     siblings
    1.05
    ть
    1.04
    s
    1.01
    ח
    0.97
    0
    0.96
    Act Density 0.003%

    No Known Activations