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

    Neuronpedia

    INDEX
    Explanations

    opportunities and early warning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.59
     be
    0.55
    ال
    0.49
    يل
    0.42
     are
    0.41
     It
    0.41
     as
    0.40
    Ti
    0.39
    تم
    0.38
    0.38
    POSITIVE LOGITS
    n
    0.52
    ა
    0.50
    .}(
    0.49
    h
    0.49
    ._
    0.49
    (
    0.48
    .(
    0.47
    9
    0.46
    .³
    0.46
    грамма
    0.46
    Act Density 0.099%

    No Known Activations