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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.77
    í
    0.75
    E
    0.69
     It
    0.66
    ä
    0.64
     निकालेंगे
    0.63
    !
    0.63
    ↵↵↵↵
    0.61
    <unused1827>
    0.60
    <unused601>
    0.58
    POSITIVE LOGITS
     comentar
    0.73
    n
    0.72
     constitue
    0.69
     crece
    0.66
    ي
    0.66
     fáb
    0.66
    ov
    0.64
     в
    0.64
     фигу
    0.64
    ၿ
    0.64
    Act Density 0.448%

    No Known Activations