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

    Neuronpedia

    INDEX
    Explanations

    mechanism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (errors
    -0.07
     pointed
    -0.07
     zenith
    -0.07
     попыт
    -0.07
     Israel
    -0.06
    .GetAxis
    -0.06
     coupe
    -0.06
    Mail
    -0.06
    ерап
    -0.06
    Make
    -0.06
    POSITIVE LOGITS
    醒
    0.07
     Immun
    0.06
    lassen
    0.06
     foreseeable
    0.06
     optimizer
    0.06
    Single
    0.06
     almond
    0.06
    adaptive
    0.06
    iggs
    0.06
    幅
    0.06
    Act Density 0.021%

    No Known Activations