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

    Neuronpedia

    INDEX
    Explanations

    narrative snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on positive evaluative language—words expressing approval or praise (e.g. “amazing,” “great,” “love it”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Tmp
    -0.06
    يدي
    -0.06
    ิ
    -0.06
    Dup
    -0.06
    २
    -0.06
    ись
    -0.06
    ienie
    -0.06
     medicinal
    -0.06
    вал
    -0.06
    isque
    -0.06
    POSITIVE LOGITS
     обращ
    0.07
    chrono
    0.07
    	info
    0.06
     Speech
    0.06
     unilateral
    0.06
    ından
    0.06
    Charlotte
    0.06
     *)"
    0.06
     qualifier
    0.06
     ora
    0.06
    Act Density 0.163%

    No Known Activations