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

    Neuronpedia

    INDEX
    Explanations

    win

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    땅
    -0.08
     natur
    -0.08
     imgs
    -0.07
    县城
    -0.07
    (pdf
    -0.07
     mall
    -0.07
    -cigarettes
    -0.07
     כתוצאה
    -0.07
     gratuites
    -0.07
     devices
    -0.07
    POSITIVE LOGITS
    moved
    0.06
    .Checked
    0.06
    рог
    0.06
     =
↵
    0.06
     предмет
    0.06
    你好
    0.06
    (project
    0.06
    roy
    0.06
    smooth
    0.06
     Herbert
    0.06
    Act Density 0.017%

    No Known Activations