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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    質
    -0.06
    تو
    -0.06
     prop
    -0.06
     концеп
    -0.06
     reput
    -0.06
    味
    -0.06
     resist
    -0.06
    _"
    -0.06
     adjective
    -0.06
    <Integer
    -0.06
    POSITIVE LOGITS
    Ｅ
    0.07
     impover
    0.07
    pike
    0.06
    幸
    0.06
    EXT
    0.06
     розви
    0.06
    ıyor
    0.06
     khả
    0.06
    =\
    0.06
     şu
    0.06
    Act Density 0.007%

    No Known Activations