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

    Neuronpedia

    INDEX
    Explanations

    serious and concerning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ि
    0.49
     хра
    0.49
     foreclosure
    0.48
     Địa
    0.48
     nếu
    0.46
     depreciation
    0.46
     বেদনা
    0.46
    iczne
    0.45
     vielleicht
    0.45
    َى
    0.45
    POSITIVE LOGITS
    re
    0.46
    مر
    0.46
    locked
    0.45
    ads
    0.44
    were
    0.43
    اول
    0.41
    st
    0.41
    fl
    0.41
    дем
    0.41
    picked
    0.40
    Act Density 0.001%

    No Known Activations