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

    Neuronpedia

    INDEX
    Explanations

    response generation scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hands
    0.46
    রা
    0.45
    ocrats
    0.43
    ラジオ
    0.43
    ću
    0.42
    such
    0.42
     הג
    0.42
    square
    0.41
    世界
    0.41
    libro
    0.40
    POSITIVE LOGITS
     ladd
    0.49
     deterioro
    0.48
     searchValue
    0.46
     wynik
    0.44
     subsid
    0.44
     memberikan
    0.43
    纓
    0.43
     അധിക
    0.42
     karn
    0.41
     gra
    0.40
    Act Density 0.002%

    No Known Activations