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

    Neuronpedia

    INDEX
    Explanations

    world-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Worldwide
    0.83
    Expo
    0.76
    håll
    0.75
    থিত
    0.75
    Every
    0.74
    Throw
    0.74
     پھی
    0.73
    Closing
    0.73
    Text
    0.72
    例外
    0.71
    POSITIVE LOGITS
     reign
    0.79
     cha
    0.79
     cannon
    0.75
     disabled
    0.72
     king
    0.72
     monster
    0.72
    ানো
    0.72
     disability
    0.72
     fed
    0.71
     dragon
    0.70
    Act Density 0.007%

    No Known Activations