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

    Neuronpedia

    INDEX
    Explanations

    Si ifra, om bøker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zunächst
    0.32
     virksom
    0.31
     इसमें
    0.31
    indeki
    0.30
     («
    0.30
     sebagaimana
    0.29
     beslut
    0.29
     neden
    0.28
     இதன்
    0.28
     באמצעות
    0.28
    POSITIVE LOGITS
     "
    0.35
     lvl
    0.34
     jaja
    0.34
    됬
    0.34
     sooo
    0.33
     soooo
    0.32
    ゎ
    0.31
     đc
    0.30
     +
    0.29
    😌
    0.29
    Act Density 0.000%

    No Known Activations