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

    Neuronpedia

    INDEX
    Explanations

    safety first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आणि
    0.60
     మరియు
    0.58
     மற்றும்
    0.55
     અને
    0.55
     и
    0.54
     और
    0.52
     ਅਤੇ
    0.52
     এবং
    0.51
     및
    0.50
     və
    0.49
    POSITIVE LOGITS
     μπορούν
    0.42
     Nhưng
    0.42
     nascost
    0.41
     möglich
    0.40
    ပြန်
    0.40
     কাছাকাছি
    0.40
    နိုင်သည်။
    0.40
     nhưng
    0.39
     possono
    0.39
     overturned
    0.39
    Act Density 0.004%

    No Known Activations