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

    Neuronpedia

    INDEX
    Explanations

    coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .variant
    -0.08
     units
    -0.08
    rac
    -0.07
     racism
    -0.07
     Units
    -0.06
     ministry
    -0.06
    .s
    -0.06
    center
    -0.06
    ms
    -0.06
    /format
    -0.06
    POSITIVE LOGITS
    ,…↵↵
    0.07
    (at
    0.07
     ):↵↵
    0.07
     )(
    0.06
    	Vec
    0.06
    езультат
    0.06
    _EFFECT
    0.06
    (""+
    0.06
    एक
    0.06
    ###############################################################################↵
    0.06
    Act Density 0.000%

    No Known Activations