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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vertical
    -0.06
     depressive
    -0.06
    ॉल
    -0.06
    _FATAL
    -0.06
    grams
    -0.06
     isc
    -0.06
     ine
    -0.06
    كم
    -0.06
    smith
    -0.06
    listen
    -0.06
    POSITIVE LOGITS
    ẩy
    0.07
     kre
    0.07
     girdi
    0.06
    буд
    0.06
     rád
    0.06
     bab
    0.06
    (':
    0.06
    -bootstrap
    0.06
     станов
    0.06
    .callback
    0.06
    Act Density 0.077%

    No Known Activations