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

    Neuronpedia

    INDEX
    Explanations

    diagnosing issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nuova
    0.44
     encour
    0.41
     그래프
    0.41
     impatiently
    0.39
     proposé
    0.38
     denote
    0.38
    າງ
    0.38
     የተለያዩ
    0.38
     gesture
    0.38
     forecasted
    0.38
    POSITIVE LOGITS
    which
    0.46
     시절
    0.46
     katol
    0.44
    henden
    0.42
     Endowment
    0.41
    nesto
    0.41
    那时候
    0.40
    㭋
    0.40
    डम
    0.40
    DE
    0.40
    Act Density 0.006%

    No Known Activations