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

    Neuronpedia

    INDEX
    Explanations

    LaTeX diagram nodes and drawing syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diagram
    0.52
     diagrams
    0.51
     Diagram
    0.47
    Position
    0.47
    diagram
    0.46
     Diagrams
    0.46
    Flow
    0.46
    Diagram
    0.45
    Arrow
    0.44
     Schematic
    0.43
    POSITIVE LOGITS
    ernacle
    0.44
    をお
    0.43
    ynd
    0.42
    鶉
    0.41
    ysuckle
    0.41
    毫不
    0.40
    दायी
    0.40
    networking
    0.40
     प्रथ
    0.40
     sureties
    0.40
    Act Density 0.011%

    No Known Activations