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

    Neuronpedia

    INDEX
    Explanations

    governing matrix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不会
    0.44
    ὧ
    0.42
    不會
    0.42
    llabus
    0.42
    inerja
    0.41
    vtk
    0.41
    விர
    0.41
     ankaŭ
    0.40
     coincided
    0.39
    contrib
    0.38
    POSITIVE LOGITS
     governing
    0.46
     slots
    0.45
     govern
    0.45
    Uses
    0.44
    Replace
    0.43
    Slots
    0.43
     Governing
    0.43
     regulating
    0.42
    Allows
    0.42
     Allow
    0.42
    Act Density 0.000%

    No Known Activations