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

    Neuronpedia

    INDEX
    Explanations

    for granted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вані
    1.58
     любо
    1.49
     disappointed
    1.45
    संपादन
    1.42
    ⚜
    1.41
     vlast
    1.41
     haunting
    1.39
    incible
    1.39
     courtyard
    1.38
    ᅴ
    1.38
    POSITIVE LOGITS
    o
    1.37
    heits
    1.19
    anut
    1.16
    ις
    1.13
    uenza
    1.11
    checkmark
    1.08
    او
    1.08
    隰
    1.05
    ל
    1.05
    此之外
    1.04
    Act Density 0.002%

    No Known Activations