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

    Neuronpedia

    INDEX
    Explanations

    python imports for plotting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Control
    0.41
    Highlight
    0.40
    nud
    0.40
    Notifier
    0.39
    Available
    0.38
    immt
    0.38
    Limite
    0.38
    available
    0.38
    Fuse
    0.37
    await
    0.37
    POSITIVE LOGITS
     SVG
    0.44
     DIR
    0.42
     übrigens
    0.42
     Ops
    0.42
     tir
    0.42
     XY
    0.41
     Typography
    0.40
     aline
    0.40
     اوس
    0.40
     tumb
    0.40
    Act Density 0.000%

    No Known Activations