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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens containing decimal points, i.e. decimal‐formatted statistics.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Мон
    -0.07
    orianCalendar
    -0.07
     VM
    -0.06
     Living
    -0.06
     документ
    -0.06
    ioneer
    -0.06
    /global
    -0.06
     displaying
    -0.06
    .pop
    -0.06
    _record
    -0.06
    POSITIVE LOGITS
    ivos
    0.07
     lanç
    0.06
    uffle
    0.06
     his
    0.06
    typeparam
    0.06
    涉
    0.06
     Var
    0.06
     biển
    0.06
    MySQL
    0.06
    028
    0.06
    Act Density 0.016%

    No Known Activations