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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash

    It responds to numeric tokens (digits or numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .FromSeconds
    -0.07
    tester
    -0.06
    Drive
    -0.06
     */,↵
    -0.06
    FileName
    -0.06
     κό
    -0.06
    EQUAL
    -0.06
     Frontier
    -0.06
     Ve
    -0.06
    ."[
    -0.06
    POSITIVE LOGITS
    identally
    0.07
    룸
    0.07
    úmeros
    0.06
    cluir
    0.06
    燃
    0.06
     taps
    0.06
    _atts
    0.06
    usi
    0.06
     exacerb
    0.06
    屬
    0.06
    Act Density 0.004%

    No Known Activations