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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric literals—specifically on floating-point numbers (decimal constants) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    icemail
    -0.07
    (requestCode
    -0.06
    าณ
    -0.06
     Kürt
    -0.06
    _logger
    -0.06
    .UTF
    -0.06
     캐
    -0.06
     bức
    -0.06
     Fac
    -0.06
    剛
    -0.06
    POSITIVE LOGITS
    thern
    0.07
     russian
    0.07
    znam
    0.06
    way
    0.06
    explain
    0.06
    ське
    0.06
    ieron
    0.06
     extra
    0.06
     azt
    0.06
    empre
    0.06
    Act Density 0.000%

    No Known Activations