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

    Neuronpedia

    INDEX
    Explanations

    mixed language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    F
    1.50
    J
    1.45
    1.43
    K
    1.41
    P
    1.40
    V
    1.38
    N
    1.38
    U
    1.36
    C
    1.34
    H
    1.34
    POSITIVE LOGITS
     scrollBody
    1.13
    ونات
    1.09
     roupas
    1.07
    っている
    1.05
     sociais
    1.05
     limpeza
    1.03
     télévision
    1.02
     samochod
    1.02
     mujeres
    1.01
     lascia
    1.01
    Act Density 1.531%

    No Known Activations