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

    Neuronpedia

    INDEX
    Explanations

    code structure and dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     информационной
    0.44
    ওল
    0.42
     polynucle
    0.42
     ratepayers
    0.42
    संख्य
    0.41
     pharmacokinetic
    0.41
     excreted
    0.40
     anastomosis
    0.40
    伢
    0.39
    ারন
    0.39
    POSITIVE LOGITS
     (
    0.40
    (
    0.40
    0.40
    test
    0.38
    1
    0.37
    {
    0.36
     {
    0.36
    /
    0.35
     [
    0.35
    でない
    0.35
    Act Density 0.006%

    No Known Activations