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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,q
    -0.07
    .docs
    -0.07
    �
    -0.07
    王朝
    -0.07
    רפואה
    -0.07
    碣
    -0.07
    	border
    -0.06
    'u
    -0.06
     Höhe
    -0.06
    _dup
    -0.06
    POSITIVE LOGITS
     "+
    0.07
     zoals
    0.07
     Marco
    0.07
    诇
    0.07
     المرأ
    0.07
    Ể
    0.07
    test
    0.07
    연
    0.06
    /disable
    0.06
    לת
    0.06
    Act Density 0.000%

    No Known Activations