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

    Neuronpedia

    INDEX
    Explanations

    operation reverses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.48
     clara
    0.48
     intelligible
    0.46
     robuste
    0.46
    Experts
    0.44
     directe
    0.44
     zvlá
    0.44
     weltweit
    0.43
     nell
    0.43
    زيد
    0.43
    POSITIVE LOGITS
    asure
    0.45
    isku
    0.45
    鈁
    0.45
    ashion
    0.44
    isty
    0.44
    ҳои
    0.44
    foy
    0.43
    farande
    0.43
    comedy
    0.43
    aik
    0.42
    Act Density 0.002%

    No Known Activations