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

    Neuronpedia

    INDEX
    Explanations

    sudden change or contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仍
    0.52
    continue
    0.47
    依然
    0.46
    ยัง
    0.46
    依旧
    0.45
    indungi
    0.44
    Continue
    0.43
    Console
    0.43
    AnyCPU
    0.42
     आजही
    0.42
    POSITIVE LOGITS
     suddenly
    1.04
     plötzlich
    0.91
    突然
    0.87
     अचानक
    0.86
     Suddenly
    0.85
     sudden
    0.79
     вдруг
    0.77
    忽然
    0.75
     হঠাৎ
    0.74
    变得
    0.71
    Act Density 0.143%

    No Known Activations