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

    Neuronpedia

    INDEX
    Explanations

    complex issue or question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arus
    0.67
    ための
    0.64
    oconut
    0.63
    glu
    0.63
     मेथ
    0.63
    ET
    0.62
    𝒐
    0.62
     doomed
    0.61
    IN
    0.61
    GRU
    0.61
    POSITIVE LOGITS
    or
    0.84
    𝐶
    0.79
    ]);
    0.66
    ″]
    0.63
    ル
    0.60
    𝑚
    0.60
     få
    0.60
    ൻ
    0.59
     século
    0.59
    ดา
    0.58
    Act Density 0.738%

    No Known Activations