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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ์ค
    -0.07
     swallowing
    -0.06
     creatively
    -0.06
     meis
    -0.06
    -story
    -0.06
    ัวเอง
    -0.06
    EventHandler
    -0.06
     Monitoring
    -0.06
    _colors
    -0.06
     hollow
    -0.06
    POSITIVE LOGITS
    .Volume
    0.07
    소년
    0.07
    IFICATION
    0.07
     CSL
    0.06
     đức
    0.06
    _AST
    0.06
    .hibernate
    0.06
    ۱۰
    0.06
    .READ
    0.06
    probante
    0.06
    Act Density 0.082%

    No Known Activations