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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strands
    -0.07
     evapor
    -0.07
    reve
    -0.07
     recipes
    -0.06
     Lite
    -0.06
    เฉล
    -0.06
     bonding
    -0.06
     villages
    -0.06
    ARD
    -0.06
    -born
    -0.06
    POSITIVE LOGITS
        ↵    ↵    ↵
    0.07
     addCriterion
    0.06
     Clinton
    0.06
    .UtcNow
    0.06
     Infect
    0.06
    ;↵↵↵↵
    0.06
     underage
    0.06
     عدم
    0.06
     Evalu
    0.06
     WANT
    0.06
    Act Density 0.400%

    No Known Activations