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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash

    This neuron specifically picks out floating‐point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     दर
    -0.07
    bic
    -0.07
    _def
    -0.07
     Defense
    -0.06
    xf
    -0.06
     nog
    -0.06
     Provid
    -0.06
    -C
    -0.06
    arse
    -0.06
    -playing
    -0.06
    POSITIVE LOGITS
    $rows
    0.07
     realm
    0.06
    ốn
    0.06
     سیستم
    0.06
     colonies
    0.06
    άνει
    0.06
     ocor
    0.06
     oportun
    0.06
    .ToDecimal
    0.06
     공간
    0.06
    Act Density 0.012%

    No Known Activations