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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mysqli
    -0.09
     מקבל
    -0.08
    賺
    -0.08
    iết
    -0.08
     ;;=
    -0.08
    ᠰ
    -0.07
     בניית
    -0.07
     ملي
    -0.07
    感じ
    -0.07
    を感じ
    -0.07
    POSITIVE LOGITS
    dance
    0.08
    .↵↵↵↵↵↵
    0.07
     traff
    0.07
    ↵↵↵↵↵↵
    0.07
     __________________________________
    0.07
     grass
    0.07
    Force
    0.07
     AB
    0.07
     bra
    0.07
     wikipedia
    0.07
    Act Density 0.015%

    No Known Activations