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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    逍遥
    -0.07
    _product
    -0.07
    至于
    -0.07
    ו
    -0.06
    斗争
    -0.06
    chimp
    -0.06
     textView
    -0.06
    病症
    -0.06
     Так
    -0.06
    .junit
    -0.06
    POSITIVE LOGITS
    acimiento
    0.07
     colle
    0.07
    指控
    0.07
    _HALF
    0.06
    _EMPTY
    0.06
    叠
    0.06
     Pregnancy
    0.06
     studs
    0.06
    _Target
    0.06
     Annex
    0.06
    Act Density 0.055%

    No Known Activations