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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🠀
    0.54
    र्‍या
    0.49
    ……..
    0.48
    ᖓ
    0.48
    }/${
    0.47
    ）【
    0.46
    .³
    0.46
    🌫
    0.45
    )>=
    0.45
    ﹙
    0.45
    POSITIVE LOGITS
     \
    1.28
    ^{\
    1.05
     (\
    1.05
     \,
    1.05
    _{\
    1.01
     {\
    0.93
     [\
    0.90
    _{
    0.88
     \;
    0.88
    ^{
    0.87
    Act Density 0.123%

    No Known Activations