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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    The neuron activates on version‐control metadata lines—revision entries, dates, version numbers, and changelog headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Birth
    -0.07
    ricular
    -0.06
    getCode
    -0.06
     Soccer
    -0.06
     deliveries
    -0.06
     McGu
    -0.06
     attain
    -0.06
    ‡
    -0.06
    .signup
    -0.06
     Brothers
    -0.06
    POSITIVE LOGITS
    щё
    0.07
    态
    0.07
     узн
    0.07
    ty
    0.06
    ань
    0.06
    ;/*
    0.06
    ژ
    0.06
    ytt
    0.06
     ged
    0.06
     "-";↵
    0.06
    Act Density 0.004%

    No Known Activations