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

    Neuronpedia

    INDEX
    Explanations

    introducing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वहीं
    1.20
    ί
    1.13
    ün
    1.09
    ма
    1.05
    Rocks
    1.05
    ти
    1.05
    ці
    1.04
    ία
    1.04
     הג
    1.03
    ilità
    1.03
    POSITIVE LOGITS
    e
    1.68
    いる
    1.28
    house
    1.26
    eosin
    1.21
    D
    1.20
    eek
    1.17
    screw
    1.16
    orit
    1.15
     wiggle
    1.15
    oras
    1.11
    Act Density 0.057%

    No Known Activations