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

    Neuronpedia

    INDEX
    Explanations

    license

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    茭
    -0.07
    -third
    -0.07
     것
    -0.07
    民政局
    -0.07
     יה
    -0.07
    鳳
    -0.06
     lipstick
    -0.06
     suff
    -0.06
    쯧
    -0.06
    -html
    -0.06
    POSITIVE LOGITS
    אנגלית
    0.07
    充满
    0.07
    Sys
    0.07
     persecution
    0.07
     witches
    0.07
     subdued
    0.07
    Enemy
    0.07
    对外
    0.07
    WebResponse
    0.07
    )+'
    0.06
    Act Density 0.002%

    No Known Activations