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

    Neuronpedia

    INDEX
    Explanations

    Sentry SDK configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Konz
    -0.09
     Ellen
    -0.08
     खराब
    -0.08
     कमज
    -0.08
     Bulgar
    -0.08
     malad
    -0.08
     failure
    -0.08
    eschichte
    -0.08
     Тер
    -0.08
     болез
    -0.08
    POSITIVE LOGITS
    sampling
    0.10
    _sampling
    0.10
     Sampling
    0.09
    Sampling
    0.09
     sampling
    0.09
     Traffic
    0.09
     traffic
    0.09
    _SAMPLE
    0.08
    /sample
    0.08
     every
    0.08
    Act Density 0.003%

    No Known Activations