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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash

    The neuron fires on the string‐format specifier “%s” (i.e. when a printf/ sprintf format includes “%s”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     But
    -0.07
    deal
    -0.07
    ають
    -0.06
    ,-
    -0.06
     franç
    -0.06
     flexGrow
    -0.06
    .readInt
    -0.06
    ตำ
    -0.06
     lookahead
    -0.06
     expérience
    -0.06
    POSITIVE LOGITS
    ghan
    0.07
    سن
    0.07
    opsis
    0.07
    atisation
    0.07
    ิส
    0.07
    印
    0.07
    serrat
    0.07
    ssi
    0.07
    ()['
    0.07
     salsa
    0.06
    Act Density 0.003%

    No Known Activations