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

    Neuronpedia

    INDEX
    Explanations

    confusion

    np_max-act · gemini-2.0-flash

    The neuron detects words expressing confusion or perplexity (e.g. “baffled,” “perplexed”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    好的
    -0.07
    dispatcher
    -0.07
    :item
    -0.06
    電影
    -0.06
    .bunifu
    -0.06
    |array
    -0.06
    ulares
    -0.06
     inv
    -0.06
     Σεπ
    -0.06
    .correct
    -0.06
    POSITIVE LOGITS
     puzzled
    0.10
     perplex
    0.09
     baff
    0.08
    (__
    0.07
    MET
    0.07
     vex
    0.07
     HT
    0.07
     scrambling
    0.06
    affle
    0.06
     bem
    0.06
    Act Density 0.010%

    No Known Activations