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

    Neuronpedia

    INDEX
    Explanations

    LaTeX and code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Madonna
    0.98
     SS
    0.88
     lantern
    0.84
     Pinn
    0.83
     epit
    0.83
     lamp
    0.83
     baroque
    0.82
     AVG
    0.81
     Lightning
    0.81
     Baroque
    0.80
    POSITIVE LOGITS
    tex
    2.62
     tex
    1.61
    TEX
    1.52
    Tex
    1.51
     TEX
    1.40
    TeX
    1.39
     Tex
    1.29
    latex
    1.20
    text
    1.10
    langle
    1.06
    Act Density 0.000%

    No Known Activations