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

    Neuronpedia

    INDEX
    Explanations

    0 or 100

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obs
    -0.07
     Tits
    -0.07
    τερο
    -0.07
    anuts
    -0.06
     versatile
    -0.06
    Corn
    -0.06
     Beard
    -0.06
     aes
    -0.06
    safe
    -0.06
     rizik
    -0.06
    POSITIVE LOGITS
     ตำ
    0.07
    .GraphicsUnit
    0.07
     enlight
    0.06
     Martha
    0.06
    ;*/↵
    0.06
    付
    0.06
     patri
    0.06
    				
↵
    0.06
     Otherwise
    0.06
     DataContext
    0.06
    Act Density 0.026%

    No Known Activations