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

    Neuronpedia

    INDEX
    Explanations

    text decoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RING
    0.43
     अधूरा
    0.40
    accumulator
    0.40
    popUp
    0.40
    dropDown
    0.40
    धू
    0.39
     gambler
    0.38
    偿
    0.38
    하시
    0.37
     tema
    0.37
    POSITIVE LOGITS
    Change
    0.41
     converts
    0.39
     Royce
    0.38
     conversion
    0.37
     coll
    0.36
     conversions
    0.36
    oplasm
    0.36
     changeable
    0.35
     convers
    0.34
    conversion
    0.34
    Act Density 0.001%

    No Known Activations