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
     cannabinoids
    -0.07
     PEN
    -0.07
     cash
    -0.07
     банку
    -0.07
    水
    -0.06
     rainbow
    -0.06
    andard
    -0.06
    ců
    -0.06
    aylor
    -0.06
     куль
    -0.06
    POSITIVE LOGITS
     Haz
    0.08
     earners
    0.06
    र
    0.06
    _ARGS
    0.06
     seriousness
    0.06
     bool
    0.06
    حل
    0.06
     şimdi
    0.06
     جهت
    0.06
    _precision
    0.05
    Act Density 0.000%

    No Known Activations