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

    Neuronpedia

    INDEX
    Explanations

    code snippets with React syntax, especially related to views and components

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.74
    <bos>
    -0.71
    UnusedPrivate
    -0.70
    دانشنامهٔ
    -0.69
     carico
    -0.68
    IUrlHelper
    -0.66
     kasarigan
    -0.60
     démocratie
    -0.59
     GenerationType
    -0.57
    ftagPool
    -0.57
    POSITIVE LOGITS
    UCN
    0.56
    phis
    0.50
    省市镇
    0.47
    ':{'
    0.46
    mae
    0.44
    ://$
    0.43
    MIND
    0.43
    modb
    0.43
     waw
    0.43
     Mer
    0.43
    Act Density 1.597%

    No Known Activations