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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    This neuron detects numeric decimal values in the text (numbers with a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Save
    -0.09
    -Muslim
    -0.07
    quete
    -0.07
    sled
    -0.07
    =<?=$
    -0.06
     devote
    -0.06
    itect
    -0.06
    cak
    -0.06
    etxt
    -0.06
    Rep
    -0.06
    POSITIVE LOGITS
     envi
    0.06
     liệt
    0.06
     morphology
    0.06
     artık
    0.06
     cette
    0.06
     permutations
    0.06
     صرف
    0.06
     س
    0.06
    ,I
    0.06
     каль
    0.06
    Act Density 0.053%

    No Known Activations