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

    Neuronpedia

    INDEX
    Explanations

    null/boolean values

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of programming “nullish” literal tokens indicating a missing or undefined value.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    strpos
    -0.06
    Li
    -0.06
    特
    -0.06
    _THREAD
    -0.06
    postcode
    -0.06
     Lorenzo
    -0.06
     méthode
    -0.06
     bicycle
    -0.06
    θη
    -0.06
    Inverse
    -0.06
    POSITIVE LOGITS
     dağı
    0.07
     insiders
    0.07
    (EC
    0.06
    Sept
    0.06
    .APP
    0.06
     QUERY
    0.06
    _SYN
    0.06
     只
    0.06
    :Set
    0.06
     бли
    0.06
    Act Density 0.013%

    No Known Activations