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

    Neuronpedia

    INDEX
    Explanations

    global context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     optimism
    -0.07
     novelist
    -0.07
    ��
    -0.07
    inium
    -0.07
     unbe
    -0.07
    ét
    -0.06
     bastante
    -0.06
     diag
    -0.06
    -points
    -0.06
     хозя
    -0.06
    POSITIVE LOGITS
    .archive
    0.08
     startups
    0.07
    -Control
    0.06
     lets
    0.06
    Nike
    0.06
    _gettime
    0.06
     Then
    0.06
    toThrow
    0.06
     GPUs
    0.06
     kort
    0.06
    Act Density 0.000%

    No Known Activations