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

    Neuronpedia

    INDEX
    Explanations

    question starters and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    歡
    0.48
    tau
    0.47
     HINSTANCE
    0.43
     foams
    0.42
    tob
    0.41
     எடுத்துக்கா
    0.40
    rocessing
    0.40
    neş
    0.40
     encir
    0.40
     gneiss
    0.40
    POSITIVE LOGITS
    _
    0.57
     \
    0.52
    Facilities
    0.52
    Faculty
    0.50
    Registration
    0.49
     डेटा
    0.47
    ถ่าย
    0.47
    Cage
    0.46
    Elena
    0.46
    သ
    0.46
    Act Density 0.000%

    No Known Activations