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

    Neuronpedia

    INDEX
    Explanations

    discount

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of discount or reduction terms—especially “reduction” and related percentage‐of discount references.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     BATCH
    -0.07
    싸
    -0.07
    .mime
    -0.06
    /lists
    -0.06
    .force
    -0.06
    前の
    -0.06
     dread
    -0.06
    +'.
    -0.06
     Nep
    -0.06
    <Double
    -0.06
    POSITIVE LOGITS
     clientId
    0.07
    /dis
    0.07
     embodiments
    0.07
     outfile
    0.06
    (em
    0.06
     inhabitants
    0.06
     सम
    0.06
    _DISPLAY
    0.06
    !↵↵
    0.06
    Mul
    0.06
    Act Density 0.011%

    No Known Activations