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

    Neuronpedia

    INDEX
    Explanations

    alerts and warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     automorphisms
    0.46
    низ
    0.45
    angels
    0.40
    αιρε
    0.40
     সুস্পষ্ট
    0.39
    否定
    0.39
    녜
    0.39
     Rejected
    0.38
    btns
    0.38
    遺跡
    0.38
    POSITIVE LOGITS
    [!
    0.43
     conc
    0.41
     urbano
    0.41
     total
    0.40
    范
    0.40
     habit
    0.40
     Webb
    0.39
     con
    0.39
     union
    0.39
     Northwest
    0.38
    Act Density 0.001%

    No Known Activations