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

    Neuronpedia

    INDEX
    Explanations

    descriptions and comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ·
    -0.07
    性
    -0.07
     filament
    -0.06
    丁目
    -0.06
    י�
    -0.06
    vehicle
    -0.06
    Temp
    -0.06
    �璃
    -0.06
    措施
    -0.06
    ц
    -0.06
    POSITIVE LOGITS
    				
↵
    0.07
    _close
    0.07
     घ
    0.07
     unsus
    0.07
    ){
↵
    0.07
    getDb
    0.06
    �
    0.06
    952
    0.06
    	
↵
↵
    0.06
    )((((
    0.06
    Act Density 0.090%

    No Known Activations