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

    Neuronpedia

    INDEX
    Explanations

    forces behind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ንዳንድ
    0.37
     identifiers
    0.30
     коюмдар
    0.30
    शिता
    0.30
     fillColorSpace
    0.30
     Букмекердик
    0.29
     şeyler
    0.29
    िशनर
    0.29
    ሃኒ
    0.29
     difficultés
    0.29
    POSITIVE LOGITS
     (
    0.33
    :
    0.32
    0.31
    -
    0.30
     و
    0.30
    ־
    0.29
     لأن
    0.28
     oraz
    0.28
     miraculously
    0.27
    Which
    0.27
    Act Density 0.129%

    No Known Activations