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

    Neuronpedia

    INDEX
    Explanations

    monitoring, Max, safe, heavily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     possibilità
    0.43
    ad
    0.42
     area
    0.40
     artik
    0.39
    Builder
    0.38
    مش
    0.38
    1
    0.38
    <
    0.38
     phẳng
    0.38
    rel
    0.37
    POSITIVE LOGITS
    কিন্ত
    0.48
    මණ
    0.48
     किंतु
    0.47
    𝚎
    0.47
    CONCLUSIONS
    0.46
    ि
    0.46
    ቿ
    0.46
    Ļ
    0.46
    ດ້
    0.46
    ത്വം
    0.45
    Act Density 0.000%

    No Known Activations