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

    Neuronpedia

    INDEX
    Explanations

    including elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.48
    le
    0.43
    ass
    0.43
     dépens
    0.42
    d
    0.42
    ੨
    0.42
    ou
    0.41
    ate
    0.41
    ヨ
    0.40
    ent
    0.40
    POSITIVE LOGITS
     včetně
    0.49
     including
    0.47
    INCLUDING
    0.45
     کرمان
    0.44
     gratifying
    0.43
     inklusive
    0.43
     roof
    0.42
     alkalies
    0.42
     Three
    0.42
     thatched
    0.42
    Act Density 0.003%

    No Known Activations