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

    Neuronpedia

    INDEX
    Explanations

    measurements and averages

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric measurement values (especially decimal quantities) reported in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _SWITCH
    -0.07
    unic
    -0.06
    UID
    -0.06
    atr
    -0.06
    .bad
    -0.06
    GL
    -0.06
    UR
    -0.06
    URE
    -0.06
    ز
    -0.06
    Minimum
    -0.06
    POSITIVE LOGITS
    ,[
    0.07
    (ll
    0.07
    义
    0.07
    /*↵↵
    0.06
    ,p
    0.06
     Aydın
    0.06
     AppModule
    0.06
     $('
    0.06
     serve
    0.06
     Shops
    0.06
    Act Density 0.012%

    No Known Activations