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

    Neuronpedia

    INDEX
    Explanations

    css class names and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     A
    0.71
    Ը
    0.63
    A
    0.56
     möglichen
    0.55
    ，《
    0.54
    ，
    0.53
     is
    0.52
     (
    0.52
    但是在
    0.52
     αλλά
    0.52
    POSITIVE LOGITS
    ון
    0.59
     nuestro
    0.57
    ed
    0.56
     veliki
    0.56
    ond
    0.54
    in
    0.54
    ок
    0.54
    on
    0.53
     debajo
    0.53
    ında
    0.53
    Act Density 0.151%

    No Known Activations