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

    Neuronpedia

    INDEX
    Explanations

    eligible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Taken
    -0.07
     Emmanuel
    -0.07
    rau
    -0.07
     Carne
    -0.07
    dna
    -0.07
     மனித
    -0.07
    DNA
    -0.07
    เด
    -0.07
     Antoine
    -0.07
     கார
    -0.07
    POSITIVE LOGITS
    资格
    0.11
    Eligibility
    0.11
     eligibility
    0.10
     Eligibility
    0.10
    Criteria
    0.10
     eligible
    0.10
     criteria
    0.10
     Criteria
    0.09
     critères
    0.08
     critérios
    0.08
    Act Density 0.014%

    No Known Activations