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

    Neuronpedia

    INDEX
    Explanations

    '

    np_max-act · gemini-2.0-flash

    This neuron detects code‐style identifiers and bug/issue keys (e.g. “SOLR-4818”, “RemoveDefaultCore”, “Refactorings”) in technical text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     incorporates
    -0.07
     once
    -0.07
    AC
    -0.07
     Moments
    -0.07
     surfaces
    -0.06
    ／
    -0.06
    	T
    -0.06
    674
    -0.06
    फ
    -0.06
     graffiti
    -0.06
    POSITIVE LOGITS
    unft
    0.07
     žena
    0.06
     Yayın
    0.06
    ‌المللی
    0.06
     trabal
    0.06
    .ElementAt
    0.06
    toArray
    0.06
     Mime
    0.06
    .timeScale
    0.06
     Spoj
    0.06
    Act Density 0.279%

    No Known Activations