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
    phot
    -0.07
    or
    -0.07
    .Horizontal
    -0.06
     cí
    -0.06
    oleans
    -0.06
    /h
    -0.06
     е
    -0.06
     explo
    -0.06
    těz
    -0.06
    Arial
    -0.06
    POSITIVE LOGITS
     Twenty
    0.07
     Thick
    0.06
     Smoking
    0.06
    тиров
    0.06
    _ERROR
    0.06
    -gray
    0.06
    権
    0.06
    -redux
    0.06
    ưa
    0.06
     abide
    0.06
    Act Density 0.001%

    No Known Activations