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

    Neuronpedia

    INDEX
    Explanations

    great

    np_max-act · gemini-2.0-flash

    The neuron activates on subjective, evaluative adjectives and adverbs (e.g. great, significant, urgent) that express emphasis or strong positive appraisal.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ilst
    -0.07
     crawling
    -0.06
     anonymously
    -0.06
    .selector
    -0.06
    HasBeenSet
    -0.06
    asury
    -0.06
     luckily
    -0.06
     органов
    -0.06
    illow
    -0.06
    standing
    -0.06
    POSITIVE LOGITS
    门
    0.07
     همچ
    0.07
     图
    0.07
     strugg
    0.07
    Music
    0.06
    题
    0.06
     عراق
    0.06
    唱
    0.06
    _<
    0.06
    �
    0.06
    Act Density 0.090%

    No Known Activations