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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vase
    -0.07
    (filePath
    -0.07
     השנה
    -0.07
    🥾
    -0.06
    מחלות
    -0.06
     Dimensions
    -0.06
    옂
    -0.06
    Hop
    -0.06
    何か
    -0.06
    公关
    -0.06
    POSITIVE LOGITS
     dụng
    0.08
    _US
    0.07
    ____
    0.07
     destroyed
    0.07
    utar
    0.07
     Contents
    0.06
    graf
    0.06
    囊
    0.06
     problematic
    0.06
    CR
    0.06
    Act Density 0.003%

    No Known Activations