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

    Neuronpedia

    INDEX
    Explanations

    var

    np_max-act · gemini-2.0-flash

    This neuron detects decimal number literals (floating-point constants) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Philadelphia
    -0.07
     sním
    -0.07
    かに
    -0.07
     nebu
    -0.06
     Trudeau
    -0.06
     childhood
    -0.06
    (UIAlertAction
    -0.06
     отп
    -0.06
    .press
    -0.06
     RAF
    -0.06
    POSITIVE LOGITS
     api
    0.06
    _bo
    0.06
    cv
    0.06
     Templates
    0.06
    Optimizer
    0.06
    cran
    0.06
    ov
    0.06
    $search
    0.06
    ろ
    0.06
     pace
    0.06
    Act Density 0.001%

    No Known Activations