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

    Neuronpedia

    INDEX
    Explanations

    Sax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دنبال
    -0.07
     پل
    -0.07
     Starts
    -0.06
    Schedulers
    -0.06
    _CHO
    -0.06
    olated
    -0.06
    Tip
    -0.06
    	uv
    -0.06
    _pag
    -0.06
     Dungeon
    -0.06
    POSITIVE LOGITS
     ي
    0.07
    ﾌ
    0.07
    681
    0.07
     XX
    0.07
     Texans
    0.07
    ังค
    0.06
     FOX
    0.06
     autres
    0.06
    stage
    0.06
     노출
    0.06
    Act Density 0.002%

    No Known Activations