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

    Neuronpedia

    INDEX
    Explanations

    the end of sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.64
     W
    0.56
     in
    0.51
    im
    0.51
    il
    0.49
     ሁለት
    0.48
    ai
    0.46
     prevision
    0.46
    w
    0.45
    al
    0.44
    POSITIVE LOGITS
    0.63
    داء
    0.44
    লস
    0.43
    لي
    0.42
     ríos
    0.42
    大
    0.41
    ):
    0.41
    مركز
    0.40
    سي
    0.38
    .):
    0.38
    Act Density 0.001%

    No Known Activations