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

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .struct
    -0.26
    struct
    -0.26
     scav
    -0.25
    .keep
    -0.24
    Struct
    -0.24
     Sketch
    -0.24
     Keep
    -0.24
    å®ĺåı¸
    -0.24
     Klo
    -0.24
    .dest
    -0.24
    POSITIVE LOGITS
    é¤IJ
    0.28
    ãĤ·ãĥ§ãĥ¼
    0.26
    atedRoute
    0.26
    ukes
    0.25
    -pane
    0.25
    è¿ŀç»Ń
    0.25
    亮度
    0.24
    belt
    0.24
    FUN
    0.24
    ULA
    0.24
    Act Density 3.126%

    No Known Activations