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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document markup tags

    oai_token-act-pair · gemini-2.0-flash

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.90
     NSCoder
    -0.90
    OGND
    -0.85
     nahilalakip
    -0.82
    AddTagHelper
    -0.80
     متعلقه
    -0.77
    IsMutable
    -0.77
     שוליים
    -0.75
    ]),
    -0.75
     pinulongan
    -0.74
    POSITIVE LOGITS
     -
    0.56
    pari
    0.47
    achsen
    0.45
     тонн
    0.45
     Rankin
    0.45
     tis
    0.44
     organizing
    0.44
    o
    0.44
     ton
    0.44
     slo
    0.43
    Act Density 1.945%

    No Known Activations