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

    Neuronpedia

    INDEX
    Explanations

    specific access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     embal
    0.48
    trasound
    0.47
     brindar
    0.43
     önces
    0.43
     औष
    0.42
     biops
    0.42
     récit
    0.42
     begle
    0.41
     cartil
    0.41
     السؤال
    0.41
    POSITIVE LOGITS
     specific
    0.66
     specifically
    0.63
     wildcard
    0.61
     특정
    0.59
     Specifically
    0.59
    特定的
    0.57
    Specifically
    0.57
     spécifique
    0.56
    特定
    0.55
    权限
    0.54
    Act Density 0.206%

    No Known Activations