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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on individual tokens that are chemical element symbols or related formula components (e.g. “Cl,” “Br,” “I,” “Cu–X,” “=”), effectively detecting parts of chemical formulas.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    =""
    -0.08
     verbosity
    -0.07
    Determin
    -0.06
     مرک
    -0.06
    _COMPLEX
    -0.06
    Bear
    -0.06
     GTX
    -0.06
    MarshalAs
    -0.06
     perceptions
    -0.06
     میلی
    -0.06
    POSITIVE LOGITS
    .models
    0.07
     ngOnInit
    0.07
    ubo
    0.07
    ’da
    0.06
    agne
    0.06
     гол
    0.06
     serviceProvider
    0.06
    .gravity
    0.06
    (option
    0.06
     králov
    0.06
    Act Density 0.007%

    No Known Activations