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

    Neuronpedia

    INDEX
    Explanations

    Community

    np_max-act · gemini-2.0-flash

    This neuron activates on multi‐word, capitalized headings or titles (e.g. names of acts, reports, events, or organizational titles).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     calls
    -0.06
     infections
    -0.06
     Healing
    -0.06
     elm
    -0.06
     onions
    -0.06
    ITAL
    -0.06
     coating
    -0.06
    _snapshot
    -0.06
    erdings
    -0.06
     balcon
    -0.06
    POSITIVE LOGITS
    prene
    0.07
     arası
    0.07
    ทาง
    0.06
    荐
    0.06
    .align
    0.06
    ezier
    0.06
     relação
    0.06
    .propTypes
    0.06
     Paolo
    0.06
    ισε
    0.06
    Act Density 0.150%

    No Known Activations