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

    Neuronpedia

    INDEX
    Explanations

    breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ive
    0.29
    รับ
    0.28
    -${
    0.27
    progress
    0.26
    3
    0.26
    metik
    0.26
    你有
    0.26
    beitung
    0.26
     håll
    0.25
     möjlig
    0.25
    POSITIVE LOGITS
    א
    0.31
    ﺎ
    0.30
     ສະ
    0.30
     a
    0.27
     sfondo
    0.27
     τὰ
    0.27
     ס
    0.27
     stagione
    0.27
     '
    0.26
     Ս
    0.26
    Act Density 0.073%

    No Known Activations