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

    Neuronpedia

    INDEX
    Explanations

    Framework

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric version values (digits and decimal points) in XML project/package attributes (e.g. framework or package version numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     uğ
    -0.07
    cxx
    -0.07
     stripper
    -0.07
     principales
    -0.07
    -produ
    -0.07
    .NewReader
    -0.06
    Datetime
    -0.06
     blinds
    -0.06
     therm
    -0.06
    .CREATE
    -0.06
    POSITIVE LOGITS
     原
    0.06
    _DEF
    0.06
    UniformLocation
    0.06
     <-
    0.06
    colm
    0.06
     increase
    0.06
     控
    0.06
    (mContext
    0.06
    ,↵↵↵↵
    0.06
    伤
    0.06
    Act Density 0.001%

    No Known Activations