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

    Neuronpedia

    INDEX
    Explanations

    deterministic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.72
    Because
    0.61
    Не
    0.60
    ان
    0.59
    氐
    0.58
    كان
    0.57
    ي
    0.56
    バ
    0.56
    네
    0.55
    ে
    0.55
    POSITIVE LOGITS
    re
    0.65
     नियो
    0.55
    }}|
    0.54
    lar
    0.53
     deluxe
    0.51
     M
    0.51
     AR
    0.51
    m
    0.51
     yaptığı
    0.50
     సంవత్సర
    0.47
    Act Density 0.000%

    No Known Activations