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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allocator
    -0.06
    Radians
    -0.06
    erator
    -0.06
     Kurulu
    -0.06
    らい
    -0.06
     postfix
    -0.06
    حية
    -0.06
    ститут
    -0.06
    辅
    -0.06
    рии
    -0.06
    POSITIVE LOGITS
    .required
    0.07
    KeyDown
    0.06
     Wong
    0.06
    ￣￣
    0.06
    (models
    0.06
    _CRC
    0.06
    urst
    0.06
    _trade
    0.06
    .UTF
    0.06
    نگ
    0.06
    Act Density 0.000%

    No Known Activations