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

    Neuronpedia

    INDEX
    Explanations

    dismissing small amounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reliance
    -0.07
    	array
    -0.06
    LinkId
    -0.06
    耀
    -0.06
    Ve
    -0.06
    令人
    -0.06
    (Code
    -0.06
    	input
    -0.06
     Moment
    -0.06
    /.↵↵
    -0.06
    POSITIVE LOGITS
     rezerv
    0.07
     directed
    0.07
     MOVE
    0.07
     shoot
    0.07
    ,z
    0.06
     integrity
    0.06
    inals
    0.06
    ческой
    0.06
    (blank
    0.06
    ."""
    0.06
    Act Density 0.120%

    No Known Activations