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

    Neuronpedia

    INDEX
    Explanations

    SAM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ticks
    -0.07
     ll
    -0.07
    侵犯
    -0.07
    扫描
    -0.07
    锺
    -0.07
     copyright
    -0.07
    (gc
    -0.07
     bump
    -0.07
    .seek
    -0.07
    蜂
    -0.07
    POSITIVE LOGITS
    remain
    0.08
    ࿙
    0.07
     chấp
    0.07
    او
    0.07
    캉
    0.07
     corrobor
    0.07
    "]){↵
    0.07
     deltaY
    0.07
    établ
    0.07
     TEAM
    0.06
    Act Density 0.002%

    No Known Activations