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

    Neuronpedia

    INDEX
    Explanations

    code and math expressions

    np_max-act · gemini-2.0-flash

    The neuron activates on references to easing functions—i.e. method names or identifiers like “easeOut,” “easeIn,” and “easeInOut” defining interpolation formulas.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    isicing
    -0.07
     発
    -0.07
    ancybox
    -0.07
    remember
    -0.07
     Espresso
    -0.06
    actal
    -0.06
    ्वप
    -0.06
     tik
    -0.06
    xed
    -0.06
     recur
    -0.06
    POSITIVE LOGITS
    .Sql
    0.06
    _Mouse
    0.06
     stages
    0.06
     INV
    0.06
    INV
    0.06
     О
    0.06
    ?).
    0.06
    _units
    0.06
     chuyên
    0.06
    /Admin
    0.06
    Act Density 0.036%

    No Known Activations