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

    Neuronpedia

    INDEX
    Explanations

    code style rules and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آرام
    0.63
     شما
    0.60
     ö
    0.55
    iseite
    0.55
    au
    0.55
    vä
    0.53
     s
    0.51
     startup
    0.51
    しまう
    0.50
    خواهد
    0.50
    POSITIVE LOGITS
     Règles
    0.77
     regole
    0.72
     reglas
    0.69
     règles
    0.65
     ochron
    0.65
     Técn
    0.65
    ન્સ
    0.63
     Consultez
    0.61
     Quelles
    0.61
     Toutes
    0.60
    Act Density 0.012%

    No Known Activations