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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    考えて
    -0.07
    inspection
    -0.07
     arter
    -0.07
    _LL
    -0.06
    طف
    -0.06
     Ле
    -0.06
     анг
    -0.06
    _drag
    -0.06
     wed
    -0.06
    和睦
    -0.06
    POSITIVE LOGITS
    atican
    0.08
    위원
    0.07
     athletes
    0.07
     Taken
    0.07
     uç
    0.07
    ODULE
    0.07
    אית
    0.07
     يوليو
    0.07
     политик
    0.07
     sổ
    0.07
    Act Density 0.027%

    No Known Activations