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

    Neuronpedia

    INDEX
    Explanations

    Inclusion criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udem
    -0.08
     సందర్భ
    -0.08
    -0.07
    Lie
    -0.07
    wiki
    -0.07
     Killing
    -0.07
     neur
    -0.07
    775
    -0.07
     gagner
    -0.07
    -0.07
    POSITIVE LOGITS
     eligible
    0.12
     eligibility
    0.11
    资格
    0.11
     contraind
    0.11
    eligible
    0.11
     Eligible
    0.11
     Eligibility
    0.11
     criteria
    0.11
     Criteria
    0.10
     qualified
    0.10
    Act Density 0.011%
    No Known Activations