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

    Neuronpedia

    INDEX
    Explanations

    XML code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    941
    -0.08
    023
    -0.07
    _cycle
    -0.07
     perpet
    -0.07
    _pow
    -0.07
    Cycle
    -0.07
    .collection
    -0.07
    _pd
    -0.07
     Lucas
    -0.07
    Lucas
    -0.07
    POSITIVE LOGITS
     dédi
    0.08
    àr
    0.08
     Հայ
    0.08
     yeye
    0.08
    %s
    0.08
     subida
    0.07
    -vis
    0.07
     Grischun
    0.07
     pol
    0.07
     Ղ
    0.07
    Act Density 0.003%

    No Known Activations