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

    Neuronpedia

    INDEX
    Explanations

    starting statements or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    녠
    0.54
     a
    0.52
     commenters
    0.50
     ನಂತರ
    0.49
     commentators
    0.49
     (
    0.49
    芢
    0.48
     konsumen
    0.48
     छात्रों
    0.48
     이후
    0.48
    POSITIVE LOGITS
     be
    0.55
    ↵
    0.52
    2
    0.47
    ポ
    0.46
     cài
    0.46
    </strong>
    0.45
     vodu
    0.45
     gì
    0.45
     can
    0.45
     করিয়াছে
    0.43
    Act Density 0.194%

    No Known Activations