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

    Neuronpedia

    INDEX
    Explanations

    common

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beet
    -0.07
    Ups
    -0.07
    拍
    -0.06
    -wave
    -0.06
    شاه
    -0.06
           ↵
    -0.06
     Пер
    -0.06
     Paz
    -0.06
     brag
    -0.06
     انج
    -0.06
    POSITIVE LOGITS
     common
    0.09
     Common
    0.09
    missible
    0.07
    omap
    0.07
    �
    0.06
    Common
    0.06
    apanese
    0.06
     recommending
    0.06
     ALLOW
    0.06
     immutable
    0.06
    Act Density 0.009%

    No Known Activations