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

    Neuronpedia

    INDEX
    Explanations

    wait for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veroor
    0.34
    Als
    0.31
    ោះ
    0.30
    Tomorrow
    0.30
    volence
    0.30
    Cuánto
    0.30
     strangers
    0.29
    перед
    0.29
    Weiter
    0.29
    거나
    0.29
    POSITIVE LOGITS
     until
    0.33
    until
    0.29
     mempelajari
    0.28
     lign
    0.28
    alogical
    0.28
    直到
    0.28
     Marc
    0.28
    近年来
    0.28
     배웠
    0.27
     toki
    0.27
    Act Density 0.004%

    No Known Activations