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

    Neuronpedia

    INDEX
    Explanations

    de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     σου
    -0.07
    .bounds
    -0.07
    獲得
    -0.07
     weakness
    -0.06
    Addresses
    -0.06
    _ignore
    -0.06
     escapes
    -0.06
    iks
    -0.06
    пис
    -0.06
     จำ
    -0.06
    POSITIVE LOGITS
    PRECATED
    0.07
    /fs
    0.07
    ,g
    0.07
    .category
    0.06
     QE
    0.06
     Ihnen
    0.06
     advisable
    0.06
     targetType
    0.06
     *\
    0.06
    ivas
    0.06
    Act Density 0.078%

    No Known Activations