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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of ordinal enum member names (e.g. “First”, “Second”, “Third”) in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bao
    -0.06
     LM
    -0.06
     PROP
    -0.06
     Wat
    -0.06
    iei
    -0.06
     الرح
    -0.06
    mutable
    -0.06
    -ag
    -0.06
     negotiation
    -0.06
    _alg
    -0.06
    POSITIVE LOGITS
    rd
    0.08
     entsprech
    0.07
     perse
    0.07
    .First
    0.06
    ْد
    0.06
     하나
    0.06
    df
    0.06
     ayr
    0.06
    урс
    0.06
     Odd
    0.06
    Act Density 0.015%

    No Known Activations