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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron is specialized to detect inline numerical statistics (decimal values such as p-values, test statistics, confidence intervals, and similar quantitative measures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     findAll
    -0.07
     Train
    -0.07
     Temple
    -0.06
     Mapper
    -0.06
     Express
    -0.06
    _week
    -0.06
    between
    -0.06
     пап
    -0.06
     dispersed
    -0.06
    .AutoComplete
    -0.06
    POSITIVE LOGITS
    ولوج
    0.07
    ere
    0.07
     Gaming
    0.06
     menj
    0.06
    <u
    0.06
    venge
    0.06
     sanitized
    0.06
    coni
    0.06
    everything
    0.06
     ออนไลน
    0.06
    Act Density 0.039%

    No Known Activations