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

    Neuronpedia

    INDEX
    Explanations

    LaTeX package loading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &__
    0.49
    پوینت
    0.40
    Tocco
    0.40
    νια
    0.39
     దశ
    0.39
     zákaz
    0.39
    🙎
    0.39
    परेशन
    0.39
     ऑफिसियल
    0.39
    IVERY
    0.38
    POSITIVE LOGITS
    amsmath
    0.67
    amssymb
    0.57
     Mathematics
    0.53
    latex
    0.53
     Latex
    0.53
     Theorem
    0.49
    geometry
    0.48
    tikz
    0.48
    amsfonts
    0.48
     theorem
    0.47
    Act Density 0.001%

    No Known Activations