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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unstyled
    0.43
    relli
    0.39
    谄
    0.39
     SPI
    0.39
     ны
    0.37
    beschreibung
    0.37
    description
    0.37
     ജീ
    0.36
    植
    0.36
     Gesch
    0.35
    POSITIVE LOGITS
    Solver
    0.46
     solver
    0.45
     आरती
    0.44
    るとき
    0.42
     Visualize
    0.42
    Visualize
    0.41
     slaughtered
    0.40
    solver
    0.40
     solvers
    0.40
    vidia
    0.39
    Act Density 0.018%

    No Known Activations