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

    Neuronpedia

    INDEX
    Explanations

    code formulas

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literals—especially floating‐point constants—embedded in code and mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rych
    -0.06
    (Index
    -0.06
     高
    -0.06
    ofs
    -0.06
    uture
    -0.06
     calibration
    -0.06
    Dimensions
    -0.06
    ved
    -0.06
    (mi
    -0.06
    boats
    -0.06
    POSITIVE LOGITS
    .Nome
    0.07
     SignIn
    0.07
     smoker
    0.07
    _Al
    0.07
     abandoned
    0.07
     чоловік
    0.07
    、↵↵
    0.06
    ців
    0.06
     Pessoa
    0.06
    .ERROR
    0.06
    Act Density 0.635%

    No Known Activations