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

    Neuronpedia

    INDEX
    Explanations

    indentations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    1.97
    f
    1.55
    า
    1.49
    in
    1.48
    '
    1.41
    h
    1.40
    p
    1.40
    et
    1.38
    b
    1.38
    w
    1.36
    POSITIVE LOGITS
     предложение
    1.05
     начало
    1.02
     actinides
    1.02
     нажа
    0.98
    ालय
    0.97
     рассказа
    0.96
     функції
    0.96
     écran
    0.95
     díg
    0.95
     aislamiento
    0.95
    Act Density 0.000%

    No Known Activations