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

    Neuronpedia

    INDEX
    Explanations

    Factorials and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    algorithm
    -0.09
    interpret
    -0.08
    broker
    -0.08
     voilà
    -0.08
    accepted
    -0.08
     Brokers
    -0.08
    perhaps
    -0.08
    allowed
    -0.08
     FAIR
    -0.08
    www
    -0.08
    POSITIVE LOGITS
     washes
    0.09
     dominates
    0.09
    (hit
    0.09
     dominating
    0.09
     domina
    0.08
     diversification
    0.08
     acidente
    0.08
     tuge
    0.08
     >=
    0.08
     kills
    0.08
    Act Density 0.019%

    No Known Activations