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

    Neuronpedia

    INDEX
    Explanations

    presentation advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vaegir
    0.48
    DanhMucSP
    0.45
    兢
    0.43
    InterfaceLine
    0.42
    featuresMatrix
    0.41
     Осо
    0.40
     নিয়
    0.39
     undeni
    0.39
     فونیټ
    0.39
     песен
    0.38
    POSITIVE LOGITS
    0
    0.43
     ment
    0.42
     m
    0.42
     polyethylene
    0.42
     assoc
    0.41
    and
    0.41
     app
    0.41
     autism
    0.40
     s
    0.40
    ￥
    0.40
    Act Density 0.066%

    No Known Activations