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

    Neuronpedia

    INDEX
    Explanations

    binary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esp
    -0.07
    โบ
    -0.07
    开拓
    -0.07
     Bene
    -0.07
    �
    -0.07
    ****************
    -0.07
     Ade
    -0.07
     Pax
    -0.07
     Fab
    -0.07
    طب
    -0.07
    POSITIVE LOGITS
    읶
    0.08
     İç
    0.07
     binary
    0.07
    .rgb
    0.07
     Binary
    0.07
     behaviour
    0.06
     כ
    0.06
    binary
    0.06
    formerly
    0.06
    (levels
    0.06
    Act Density 0.008%

    No Known Activations