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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron fires on code identifiers or keywords that start with an uppercase letter (e.g. class or constructor names and other Pascal- or CamelCase tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    xffff
    -0.07
     선거
    -0.07
    noteq
    -0.07
    초
    -0.07
     Laur
    -0.07
    .notice
    -0.06
     sagt
    -0.06
     애
    -0.06
     tàu
    -0.06
    Nuitka
    -0.06
    POSITIVE LOGITS
    ثر
    0.07
    -esque
    0.07
     beneficiary
    0.06
    ══
    0.06
     accrued
    0.06
    _PROC
    0.06
     gerek
    0.06
     aktiv
    0.06
    ━━━━━━━━━━━━━━━━
    0.06
    external
    0.06
    Act Density 0.080%

    No Known Activations