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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chez
    -0.07
     Hệ
    -0.07
     Сан
    -0.06
     attrs
    -0.06
    -token
    -0.06
    util
    -0.06
    _Res
    -0.06
     quasi
    -0.06
    anes
    -0.06
     Ş
    -0.06
    POSITIVE LOGITS
     explor
    0.07
     curiosity
    0.06
     Household
    0.06
    CLUDING
    0.06
     altering
    0.06
     YELLOW
    0.06
    并不
    0.06
    egan
    0.06
     погляд
    0.06
     fatalities
    0.06
    Act Density 0.001%

    No Known Activations