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

    Neuronpedia

    INDEX
    Explanations

    code/markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    seealso
    -0.07
    ок
    -0.07
     carb
    -0.07
    =start
    -0.07
     думку
    -0.07
     Rivers
    -0.06
     uom
    -0.06
     Поль
    -0.06
    .getAction
    -0.06
    _layers
    -0.06
    POSITIVE LOGITS
    职
    0.07
    -brand
    0.07
    责
    0.06
    불
    0.06
     unified
    0.06
     enterprises
    0.06
    -defined
    0.06
    ạnh
    0.06
     Callback
    0.06
     امر
    0.06
    Act Density 0.013%

    No Known Activations