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

    Neuronpedia

    INDEX
    Explanations

    code snippets and the words "start", "creating", "learning", "return", and "something"

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newly
    -1.50
    newly
    -1.47
    Newly
    -1.37
     Newly
    -1.34
     newer
    -1.16
    fresh
    -1.16
     fresh
    -1.13
     newest
    -1.09
     freshly
    -1.09
     novel
    -1.05
    POSITIVE LOGITS
     resourceCulture
    0.85
     ExecuteAsync
    0.82
     a
    0.77
    ագրություններ
    0.71
     esternos
    0.68
     betweenstory
    0.66
    contentLoaded
    0.65
     Réponses
    0.65
     AspNetCore
    0.65
    ьаж
    0.65
    Act Density 0.352%

    No Known Activations