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

    Neuronpedia

    INDEX
    Explanations

    entities and their associated concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蓖
    0.41
     Bingo
    0.40
     chamomile
    0.39
     ब्रेस्ट
    0.39
     Reiki
    0.38
     rhenium
    0.37
     사용하여
    0.37
     理解
    0.37
     obviamente
    0.36
    Bingo
    0.36
    POSITIVE LOGITS
     weken
    0.43
    uisine
    0.43
     altid
    0.41
    akang
    0.40
    ábado
    0.38
     cumbersome
    0.38
    renown
    0.38
    awake
    0.38
    owości
    0.38
    暮らし
    0.37
    Act Density 0.002%

    No Known Activations