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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，而
    -0.07
    !!↵↵
    -0.06
     clan
    -0.06
     belt
    -0.06
     utterly
    -0.06
    én
    -0.06
    Fo
    -0.06
    /dev
    -0.06
     commands
    -0.06
     бути
    -0.06
    POSITIVE LOGITS
    .ค
    0.08
    _AXIS
    0.07
     게시
    0.07
    (substr
    0.06
    _COLORS
    0.06
    .getFont
    0.06
    unger
    0.06
    "default
    0.06
     Lessons
    0.06
    jun
    0.06
    Act Density 0.005%

    No Known Activations