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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (unittest
    -0.07
     Calculates
    -0.06
    StringUtil
    -0.06
    роничес
    -0.06
    -0.06
    不能
    -0.06
    Cla
    -0.06
     Sri
    -0.06
    {%
    -0.06
    _variable
    -0.06
    POSITIVE LOGITS
     cann
    0.06
    imary
    0.06
    su
    0.06
    ORIZATION
    0.06
     loft
    0.06
     年
    0.06
     SOM
    0.06
    μένοι
    0.06
    анг
    0.06
    isku
    0.06
    Act Density 0.031%

    No Known Activations