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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    まで
    -0.07
    儀
    -0.07
     Ease
    -0.07
     crafted
    -0.07
    판
    -0.07
     Fraser
    -0.06
     have
    -0.06
    Norm
    -0.06
     Bits
    -0.06
     getState
    -0.06
    POSITIVE LOGITS
    絶
    0.07
     GPUs
    0.06
     dissertation
    0.06
    .hits
    0.06
    _titles
    0.06
     IonicPage
    0.06
    _coeff
    0.06
    onyms
    0.06
    .ArrayAdapter
    0.06
    BeenCalled
    0.06
    Act Density 0.073%

    No Known Activations