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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RunWith
    -0.28
    usher
    -0.28
    è·¯
    -0.27
    DJ
    -0.27
    DBC
    -0.27
    repo
    -0.26
     DISPATCH
    -0.26
    寡
    -0.26
     runners
    -0.25
     Till
    -0.25
    POSITIVE LOGITS
    ¢åįķ
    0.32
     ideal
    0.29
    chosen
    0.28
     Ideal
    0.28
    çļĦçIJĨæĥ³
    0.26
     chosen
    0.26
    ideal
    0.26
     stroke
    0.26
     Kendall
    0.26
     du
    0.25
    Act Density 0.003%

    No Known Activations