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

    Neuronpedia

    INDEX
    Explanations

    programmers

    np_max-act · gemini-2.0-flash

    The neuron identifies mentions of skilled professions or job titles (e.g., engineers, accountants, programmers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    SSIP
    -0.06
     Curl
    -0.06
     Gerald
    -0.06
     �
    -0.06
    Fire
    -0.06
    biology
    -0.06
    ине
    -0.06
    Annotation
    -0.06
     тов
    -0.05
     irre
    -0.05
    POSITIVE LOGITS
    _perms
    0.07
    endant
    0.07
     GLenum
    0.07
     lexer
    0.07
     aprend
    0.07
     něho
    0.06
    :Boolean
    0.06
    :black
    0.06
    ılmaktadır
    0.06
    ]='
    0.06
    Act Density 0.118%

    No Known Activations