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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash

    This neuron identifies the start of Intel HEX–style data lines (colon-prefixed sequences of hex digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Loki
    -0.06
    /pdf
    -0.06
    이슈
    -0.06
     종
    -0.06
     эффек
    -0.06
     Nay
    -0.06
     radians
    -0.06
     imposing
    -0.06
     konci
    -0.06
     kısa
    -0.06
    POSITIVE LOGITS
    $mail
    0.07
    .";
    0.07
    _goods
    0.07
    !important
    0.07
    usaha
    0.07
     secretion
    0.07
    _container
    0.07
    ASM
    0.06
    ,temp
    0.06
    istics
    0.06
    Act Density 0.002%

    No Known Activations