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

    Neuronpedia

    INDEX
    Explanations

    apis

    np_max-act · gemini-2.0-flash

    The neuron is keyed to tokens that appear in code‐generated file/package paths and namespace identifiers (e.g. domain names, version numbers, “google”, “ads”, “api”, “proto”, “v3”/“v5”, and the punctuation that joins them).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    749
    -0.06
    .rating
    -0.06
     mužů
    -0.06
    :min
    -0.06
    iếu
    -0.05
     бол
    -0.05
     конкур
    -0.05
    战
    -0.05
    	angle
    -0.05
    TERNAL
    -0.05
    POSITIVE LOGITS
                                  ↵
    0.07
    0.07
     improvement
    0.07
    0.07
     ();↵
    0.07
                                                ↵
    0.07
    caller
    0.07
                                ↵
    0.07
                                    ↵
    0.07
     Auditor
    0.07
    Act Density 0.003%

    No Known Activations