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

    Neuronpedia

    INDEX
    Explanations

    phrases related to professional work and collaborative projects

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ModelRenderer
    -0.45
     Rican
    -0.44
     iglesias
    -0.43
    ServletConfig
    -0.43
    ミー
    -0.43
    retan
    -0.41
    enscha
    -0.41
     (__
    -0.41
    ToServer
    -0.40
     odpowiada
    -0.40
    POSITIVE LOGITS
     виправивши
    0.81
    RegressionTest
    0.75
    hoea
    0.65
     ویکی‌پدیا
    0.63
     StatelessWidget
    0.63
    MessageTagHelper
    0.60
    XmlAccessType
    0.59
    setVerticalGroup
    0.59
    #+#
    0.59
    ,:),
    0.59
    Act Density 0.598%

    No Known Activations