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

    Neuronpedia

    INDEX
    Explanations

    hurt

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the substring “hurt,” as in “hurtful.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Moff
    -0.07
    Availability
    -0.07
    miş
    -0.06
     lateinit
    -0.06
    Pal
    -0.06
     binaries
    -0.06
     mart
    -0.06
     criminal
    -0.06
     mig
    -0.06
    amphetamine
    -0.06
    POSITIVE LOGITS
    ($__
    0.07
    atetime
    0.07
     hurt
    0.06
     Ergebn
    0.06
     joy
    0.06
    _LICENSE
    0.06
     averages
    0.06
    .velocity
    0.06
     jours
    0.06
     봐
    0.06
    Act Density 0.002%

    No Known Activations