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

    Neuronpedia

    INDEX
    Explanations

    D

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    いろ
    -0.07
    ￡
    -0.07
    喬
    -0.07
     человек
    -0.07
    有过
    -0.07
    舍
    -0.07
    (Font
    -0.07
     literal
    -0.07
     interpreting
    -0.07
    slashes
    -0.07
    POSITIVE LOGITS
     "";
    0.07
     Atl
    0.07
    长辈
    0.07
     tableName
    0.06
     Democracy
    0.06
    되
    0.06
    מה
    0.06
    יכון
    0.06
     enacted
    0.06
    ◓
    0.06
    Act Density 0.010%

    No Known Activations