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

    Neuronpedia

    INDEX
    Explanations

    holidays

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of holidays or holiday-related terms (e.g. “holiday,” “Christmas,” “Thanksgiving,” “Valentine’s Day,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    inas
    -0.07
    ceptors
    -0.07
    _print
    -0.07
    74
    -0.07
    fd
    -0.07
    Domains
    -0.06
     translation
    -0.06
     China
    -0.06
     Strong
    -0.06
    ipients
    -0.06
    POSITIVE LOGITS
     příprav
    0.06
     společ
    0.06
     sank
    0.06
    ableOpacity
    0.06
    /all
    0.06
    uele
    0.06
    (AF
    0.06
     Disconnect
    0.06
    ALAR
    0.06
     closer
    0.06
    Act Density 0.077%

    No Known Activations