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

    Neuronpedia

    INDEX
    Explanations

    Deposits, compensating, subsidiary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    2.03
    ים
    1.56
    er
    1.44
     veloce
    1.40
    ar
    1.36
    es
    1.34
    ul
    1.34
    ের
    1.30
     usare
    1.27
    ות
    1.26
    POSITIVE LOGITS
     وإن
    1.31
    ㅛ
    1.27
    ສ
    1.26
    دم
    1.24
     subsidiary
    1.24
    ادف
    1.23
    ২৬
    1.16
    キ
    1.16
     zwią
    1.16
    стам
    1.15
    Act Density 0.000%

    No Known Activations