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

    Neuronpedia

    INDEX
    Explanations

    poking fun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ATUM
    -0.89
    bolista
    -0.83
    fted
    -0.81
     bancaria
    -0.81
    ベージュ
    -0.74
    すごく
    -0.74
     dà
    -0.74
     پذ
    -0.73
    GetName
    -0.71
    然
    -0.71
    POSITIVE LOGITS
     fun
    7.03
    fun
    5.09
    Fun
    4.19
     Fun
    4.19
     FUN
    3.66
    FUN
    3.52
     Spaß
    3.06
     divertido
    2.72
     diversión
    2.41
     functor
    2.16
    Act Density 0.049%

    No Known Activations