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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on code identifiers composed of multiple subwords (e.g. CamelCase or snake_case names).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     outset
    -0.06
    ulsion
    -0.06
     fourth
    -0.06
    azar
    -0.06
     bold
    -0.06
    _sphere
    -0.06
    λώ
    -0.05
    γι
    -0.05
    ycop
    -0.05
    _stream
    -0.05
    POSITIVE LOGITS
    Ÿ
    0.07
    _CALL
    0.07
    .API
    0.07
     Sanity
    0.07
     عب
    0.07
     가격
    0.07
    枪
    0.06
     $$$
    0.06
    OUN
    0.06
    生产
    0.06
    Act Density 0.076%

    No Known Activations