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

    Neuronpedia

    INDEX
    Explanations

    not against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     پہلی
    0.52
     япон
    0.52
     Հ
    0.49
     cámara
    0.48
     cámaras
    0.48
    امہ
    0.48
     giapp
    0.48
     montagnes
    0.48
     japonesa
    0.47
     japonés
    0.47
    POSITIVE LOGITS
    ↵
    0.45
     uv
    0.44
    test
    0.44
     Biscuit
    0.43
     Insulin
    0.43
    2
    0.43
    াদ
    0.43
    ضل
    0.43
    isel
    0.42
     Inspect
    0.42
    Act Density 0.004%

    No Known Activations