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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    主義
    -0.07
    rieben
    -0.07
    национа
    -0.07
    ecake
    -0.07
    ística
    -0.06
     antid
    -0.06
    斜
    -0.06
     Tours
    -0.06
     направ
    -0.06
     arcs
    -0.06
    POSITIVE LOGITS
    就會
    0.08
     Stamina
    0.07
    Getting
    0.07
     board
    0.07
    💪
    0.07
     onslaught
    0.06
    _files
    0.06
     Years
    0.06
    	Title
    0.06
     determining
    0.06
    Act Density 0.102%

    No Known Activations