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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash

    legislation and regulations related to surveillance and privacy issues.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron primarily identifies numeric tokens or numeric expressions (e.g. numbers, decimals, and related quantity indicators).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _paid
    -0.07
    類
    -0.06
     spreadsheet
    -0.06
    FieldType
    -0.06
     '**
    -0.06
    .fs
    -0.06
    Relation
    -0.06
    ,type
    -0.06
     expend
    -0.06
    ۲۶
    -0.06
    POSITIVE LOGITS
    agle
    0.08
     powers
    0.07
     crimes
    0.07
    .synthetic
    0.07
    ixo
    0.07
    ộ
    0.07
    زو
    0.07
    プラ
    0.07
    ラク
    0.06
    ##_
    0.06
    Act Density 0.051%

    No Known Activations