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

    Neuronpedia

    INDEX
    Explanations

    eligibility

    np_max-act · gemini-2.0-flash

    The neuron detects the word “eligibility” (and its variants) in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Attacks
    -0.08
    ็อก
    -0.08
     atan
    -0.07
     आक
    -0.07
     attacks
    -0.07
    216
    -0.07
     Recorded
    -0.06
     文
    -0.06
     khắc
    -0.06
     intents
    -0.06
    POSITIVE LOGITS
     eligible
    0.16
    eligible
    0.12
     ineligible
    0.12
     Elig
    0.11
     eligibility
    0.11
     elig
    0.09
     elites
    0.09
    El
    0.08
     exhilar
    0.07
    GE
    0.07
    Act Density 0.003%

    No Known Activations