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

    Neuronpedia

    INDEX
    Explanations

    exhaust

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kara
    -0.07
     fizik
    -0.07
     Governors
    -0.07
    ayas
    -0.07
     behaviors
    -0.06
    .rule
    -0.06
    KIT
    -0.06
    gies
    -0.06
    (stack
    -0.06
    (stage
    -0.06
    POSITIVE LOGITS
     Affordable
    0.07
     للإ
    0.06
    orelease
    0.06
     спок
    0.06
    xBD
    0.06
    Executable
    0.06
    :absolute
    0.06
    kich
    0.06
     дві
    0.06
    utable
    0.06
    Act Density 0.001%

    No Known Activations