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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron detects numeric measurements and statistical data (e.g. values, counts, percentages, and parenthesized figures).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     service
    -0.07
     contingency
    -0.06
    ivers
    -0.06
     Dirk
    -0.06
    _TABLE
    -0.06
     services
    -0.06
     ($('#
    -0.06
     channel
    -0.06
    خ
    -0.06
    creenshot
    -0.06
    POSITIVE LOGITS
     #'
    0.07
     #$
    0.07
     отвеч
    0.06
    ुछ
    0.06
     Symbols
    0.06
     HBO
    0.06
    енсив
    0.06
     jde
    0.06
    _AA
    0.06
    .amazonaws
    0.06
    Act Density 0.015%

    No Known Activations