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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    روط
    -0.07
    isiyle
    -0.07
     Diana
    -0.07
     ceremonial
    -0.07
    atory
    -0.07
     colon
    -0.07
    xAC
    -0.07
    edin
    -0.07
     chan
    -0.07
     inequalities
    -0.06
    POSITIVE LOGITS
    _ax
    0.07
    978
    0.06
     spotted
    0.06
    明白
    0.06
     لازم
    0.06
     특히
    0.06
    	clock
    0.06
     ए
    0.06
    อาย
    0.06
    形式
    0.06
    Act Density 0.001%

    No Known Activations