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

    Neuronpedia

    INDEX
    Explanations

    methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]+)/
    -0.07
    ени
    -0.07
    /B
    -0.06
    cljs
    -0.06
     differential
    -0.06
     occasion
    -0.06
    ’B
    -0.06
    MouseClicked
    -0.06
    46
    -0.06
    *pow
    -0.06
    POSITIVE LOGITS
    0.07
    sports
    0.06
    äge
    0.06
    /****************************************************************************
    0.06
    Fragment
    0.06
     Verfüg
    0.06
     searchData
    0.06
     gdy
    0.06
     smear
    0.06
    最后
    0.06
    Act Density 0.024%

    No Known Activations