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

    Neuronpedia

    INDEX
    Explanations

    conjugated verbs, especially in languages other than English

    oai_token-act-pair · gemini-2.0-flash

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swam
    -0.55
     uſed
    -0.53
     dilan
    -0.51
    Broke
    -0.50
    eaked
    -0.50
     Creep
    -0.48
    EnableWeb
    -0.48
    ücks
    -0.48
    ítése
    -0.48
     imprimée
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.74
    aarrggbb
    0.72
     समीक्षक
    0.71
     Infórmanos
    0.68
    <bos>
    0.67
     AspNetCore
    0.64
     <=",
    0.63
    BeginContext
    0.63
    uxxxx
    0.63
    ViewImports
    0.62
    Act Density 4.740%

    No Known Activations