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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the string “helicase” (i.e. mentions of helicase enzymes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     numa
    -0.07
     Papa
    -0.07
    ricao
    -0.06
     pero
    -0.06
    mayı
    -0.06
    NICALL
    -0.06
    signup
    -0.06
     etkil
    -0.06
     첨부
    -0.06
     izin
    -0.06
    POSITIVE LOGITS
     hypothesis
    0.07
     Concern
    0.07
    pective
    0.07
    away
    0.06
    نی
    0.06
    543
    0.06
    eri
    0.06
    ModuleName
    0.06
     paramet
    0.06
    _misc
    0.06
    Act Density 0.003%

    No Known Activations