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

    Neuronpedia

    INDEX
    Explanations

    table of contents entries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     magnes
    0.41
     solenoid
    0.41
     például
    0.40
    atients
    0.40
     muon
    0.39
     ramus
    0.39
     hầu
    0.38
     realises
    0.38
     آپ
    0.38
    satunya
    0.38
    POSITIVE LOGITS
    SECTION
    0.74
     SECTION
    0.70
     II
    0.59
    section
    0.59
     III
    0.59
    Section
    0.59
     категория
    0.58
     Kategorie
    0.58
     subsections
    0.57
     sections
    0.56
    Act Density 0.013%

    No Known Activations