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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on scientific abbreviations and acronyms (e.g., chemical formulas, gene/protein names, measurement units).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	ext
    -0.07
    Tonight
    -0.06
     также
    -0.06
    Tele
    -0.06
    .Number
    -0.06
    Perfil
    -0.06
    ,var
    -0.06
     singing
    -0.06
     доктор
    -0.06
     infix
    -0.06
    POSITIVE LOGITS
    kn
    0.07
    icip
    0.07
    _serializer
    0.06
    ίες
    0.06
     <|
    0.06
     vin
    0.06
     verdi
    0.06
    .inf
    0.06
     getWindow
    0.06
     fiat
    0.06
    Act Density 0.075%

    No Known Activations