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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects floating-point numeric literals in code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Wat
    -0.07
    보았다
    -0.07
     goalt
    -0.07
    aland
    -0.06
     pioneering
    -0.06
    aji
    -0.06
    ática
    -0.06
     GCC
    -0.06
    Samsung
    -0.06
    MMC
    -0.06
    POSITIVE LOGITS
    Margin
    0.07
    ลล
    0.06
     Pg
    0.06
    ";
↵
    0.06
    (prop
    0.06
     περι
    0.06
     spa
    0.06
    _WHITE
    0.06
     stationed
    0.05
    pering
    0.05
    Act Density 0.000%

    No Known Activations