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

    Neuronpedia

    INDEX
    Explanations

    instantaneous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    1.60
    in
    1.23
    ン
    1.23
    ان
    1.22
    stimulating
    1.21
    iveness
    1.16
    زی
    1.16
    کی
    1.13
    می
    1.11
     جیل
    1.11
    POSITIVE LOGITS
    y
    1.38
    h
    1.32
     große
    1.28
     gesamte
    1.27
     echte
    1.27
    ك
    1.27
     z
    1.19
     urč
    1.17
     veliki
    1.16
     الحالي
    1.16
    Act Density 0.000%

    No Known Activations