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

    Neuronpedia

    INDEX
    Explanations

    Species names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fundamentally
    -0.08
     spectacular
    -0.06
     mover
    -0.06
    .plist
    -0.06
     turtles
    -0.06
    ysters
    -0.06
     asserts
    -0.06
    Comic
    -0.06
     joining
    -0.06
     esc
    -0.06
    POSITIVE LOGITS
     starší
    0.07
     coaches
    0.07
    skými
    0.07
    .flatten
    0.07
    /reference
    0.07
     NAND
    0.07
     tém
    0.07
     getClient
    0.07
     paginator
    0.06
    нюю
    0.06
    Act Density 0.081%

    No Known Activations