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

    Neuronpedia

    INDEX
    Explanations

    with/of

    np_max-act · gemini-2.0-flash

    The neuron detects numerical statistic tokens, especially floating‐point decimals (e.g. 0.2230, 2.7656).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ap
    -0.07
     Mic
    -0.07
    .stereotype
    -0.06
     بت
    -0.06
     tablet
    -0.06
    _button
    -0.06
     aisle
    -0.06
    안마
    -0.06
     mic
    -0.06
    .Ticks
    -0.06
    POSITIVE LOGITS
     juicy
    0.07
    skins
    0.06
    _ITEM
    0.06
    gere
    0.06
     entityId
    0.06
    edm
    0.06
     jugg
    0.06
    Signed
    0.06
    \"",
    0.06
    spec
    0.06
    Act Density 0.015%

    No Known Activations