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

    Neuronpedia

    INDEX
    Explanations

    leather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지
    0.91
     eficiencia
    0.84
    ہ
    0.82
     aventura
    0.82
     slučaj
    0.82
     virulence
    0.81
     Фургала
    0.80
    0.80
    鵠
    0.80
     victoire
    0.80
    POSITIVE LOGITS
    ↵
    1.18
     =
    1.13
        
    1.10
     $
    1.09
    та
    0.98
     {
    0.98
    0.95
            
    0.93
    al
    0.93
     on
    0.91
    Act Density 0.002%

    No Known Activations