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

    Neuronpedia

    INDEX
    Explanations

    data scientist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    危险
    0.48
     这些
    0.46
     由于
    0.44
     যুদ্ধের
    0.41
     شدن
    0.41
    Storage
    0.39
     русской
    0.39
    फ
    0.39
    ︵
    0.39
     हमलों
    0.38
    POSITIVE LOGITS
     Wellington
    0.46
    ing
    0.46
    ou
    0.45
     Or
    0.45
    seed
    0.44
     श्रीवास्तव
    0.44
     V
    0.44
    ushka
    0.43
    ]%
    0.42
    oun
    0.42
    Act Density 0.000%

    No Known Activations