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

    Neuronpedia

    INDEX
    Explanations

    instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OnHand
    0.45
     Statistik
    0.44
     Gautam
    0.41
     Operated
    0.41
     I
    0.40
     $(
    0.40
     Mera
    0.40
     Soldaten
    0.39
     Cupid
    0.39
     Baby
    0.38
    POSITIVE LOGITS
     ভূ
    0.49
    🛀
    0.47
     મોટા
    0.46
    什么样的
    0.46
     hört
    0.45
     escrever
    0.44
    ｋ
    0.43
     與
    0.43
     dishwasher
    0.43
    烁
    0.43
    Act Density 0.002%

    No Known Activations