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

    Neuronpedia

    INDEX
    Explanations

    how to start sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.60
    ！
    0.46
     equates
    0.46
    दमी
    0.45
     asking
    0.45
     equated
    0.45
    ことで
    0.45
     dese
    0.44
     wakeup
    0.44
    \
    0.44
    POSITIVE LOGITS
     مطالب
    0.52
    统治
    0.52
    ร
    0.46
     மரு
    0.46
     क्रा
    0.45
     குடும்ப
    0.45
    ాలపై
    0.45
     වූ
    0.45
    arit
    0.44
    ஒரு
    0.43
    Act Density 0.000%

    No Known Activations