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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Needle
    -0.07
    ’am
    -0.07
    "))))↵
    -0.07
     sovereignty
    -0.06
    _dim
    -0.06
    òng
    -0.06
    	End
    -0.06
    Strip
    -0.06
    αιν
    -0.06
    getID
    -0.06
    POSITIVE LOGITS
     jeux
    0.07
     Ти
    0.07
    .Toggle
    0.07
    中文字幕
    0.06
    .MustCompile
    0.06
    タイ
    0.06
     genitals
    0.06
     Pul
    0.06
     Snap
    0.06
    stats
    0.06
    Act Density 0.000%

    No Known Activations