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

    Neuronpedia

    INDEX
    Explanations

    laundry and detergent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.64
    ।
    0.60
    ！
    0.50
    ও
    0.50
    나
    0.48
    ۔
    0.48
    리아
    0.46
    、
    0.46
    서
    0.46
    なども
    0.44
    POSITIVE LOGITS
    h
    0.89
    n
    0.58
     enfant
    0.53
     as
    0.52
     annihil
    0.52
    y
    0.48
     aerob
    0.48
    idlo
    0.48
     entrepreneur
    0.48
     habil
    0.48
    Act Density 0.001%

    No Known Activations