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

    Neuronpedia

    INDEX
    Explanations

    Identifier

    np_max-act · gemini-2.0-flash

    The neuron is detecting identifier tokens (names of variables, functions, classes, etc.) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Thread
    -0.08
     articulated
    -0.07
    Converted
    -0.07
    vido
    -0.07
    _SH
    -0.07
    IZER
    -0.07
    Ray
    -0.06
    جمع
    -0.06
     anatomy
    -0.06
    γγελ
    -0.06
    POSITIVE LOGITS
     faaliyet
    0.06
    >?
    0.06
     indian
    0.06
     Фран
    0.06
    .utility
    0.06
     alanı
    0.06
     casi
    0.06
     Все
    0.06
    ，将
    0.06
     EVEN
    0.06
    Act Density 0.018%

    No Known Activations