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

    Neuronpedia

    INDEX
    Explanations

    say "followed by 1"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     References
    -0.08
    learning
    -0.07
    ',"
    -0.07
     article
    -0.07
    (R
    -0.07
     chuyến
    -0.07
    御
    -0.07
    物质
    -0.07
    .,
    -0.07
    (QtCore
    -0.07
    POSITIVE LOGITS
    ┱
    0.07
     RCA
    0.07
    SAFE
    0.07
     spaced
    0.07
    锉
    0.06
    wow
    0.06
    焰
    0.06
    獎
    0.06
    栐
    0.06
     overshadow
    0.06
    Act Density 0.084%

    No Known Activations