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

    Neuronpedia

    INDEX
    Explanations

    order, insist, datasets, matrices, tails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     generell
    0.28
    籵
    0.28
     değişiklik
    0.27
     negatif
    0.27
    踌
    0.27
    नाचा
    0.26
     تلیفون
    0.26
    TempVal
    0.26
    珼
    0.26
    䨘
    0.26
    POSITIVE LOGITS
     and
    0.36
     માં
    0.29
    et
    0.29
     d
    0.29
    ᱮ
    0.29
     serial
    0.28
     C
    0.27
     H
    0.27
    0.27
    and
    0.27
    Act Density 0.028%

    No Known Activations