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

    Neuronpedia

    INDEX
    Explanations

    growth, profitability, access, change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وم
    0.38
    но
    0.36
    с
    0.35
    ’
    0.35
    ock
    0.34
    3
    0.34
    ö
    0.34
    б
    0.31
    "
    0.31
    ack
    0.31
    POSITIVE LOGITS
     abdom
    0.31
     tomate
    0.31
    सँग
    0.31
     һәм
    0.30
     către
    0.30
    טן
    0.30
     sembl
    0.30
     ascetic
    0.30
     অতঃ
    0.30
     decals
    0.29
    Act Density 0.536%

    No Known Activations