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

    Neuronpedia

    INDEX
    Explanations

    say "ending -ematics"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Instantiate
    -0.07
    水
    -0.06
    	Random
    -0.06
    Sigma
    -0.06
    .getHeight
    -0.06
     lombok
    -0.06
    宮
    -0.06
    :a
    -0.06
    À
    -0.06
    Async
    -0.06
    POSITIVE LOGITS
     gute
    0.07
    _pg
    0.06
    ync
    0.06
     alignItems
    0.06
     ıs
    0.06
     werde
    0.06
    undra
    0.06
     den
    0.06
    KG
    0.06
    ickt
    0.06
    Act Density 0.001%

    No Known Activations