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

    Neuronpedia

    INDEX
    Explanations

    law citations and legal terminology

    oai_token-act-pair · gemini-2.0-flash

    zero

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.51
     uLocal
    -0.51
    }{*}{}
    -0.46
    <bos>
    -0.44
     Seeder
    -0.43
    ::_('
    -0.43
    ագրություններ
    -0.42
    verwijspagina
    -0.41
     BoxFit
    -0.41
    teenth
    -0.40
    POSITIVE LOGITS
    0
    2.42
    ０
    1.44
    ০
    1.25
    ۰
    1.17
    𝟎
    1.12
     zero
    1.06
    𝟬
    1.02
    ٠
    1.02
     zéro
    1.01
     cero
    0.96
    Act Density 12.519%

    No Known Activations