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

    Neuronpedia

    INDEX
    Explanations

    list or iterable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Willard
    0.39
     Treg
    0.39
     Creme
    0.38
     acceso
    0.37
    toFloat
    0.37
    ध
    0.37
     technicians
    0.37
     COPY
    0.36
     Tac
    0.36
     ponies
    0.36
    POSITIVE LOGITS
     iterable
    1.59
    Iterable
    1.57
     Iterable
    1.54
    iterable
    1.53
     iter
    1.30
    iter
    1.23
    迭代
    1.18
    Iter
    1.16
     Iter
    1.16
     Iterator
    1.10
    Act Density 0.208%

    No Known Activations