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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles and papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "/"

    np_acts-logits-general · gemini-2.0-flash

    paper citations and DOIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    études
    -0.46
     lèvres
    -0.45
    outbound
    -0.45
    ysław
    -0.44
    RenderAtEndOf
    -0.44
     виправивши
    -0.44
    falgar
    -0.44
    ñones
    -0.43
    Sign
    -0.43
     žaid
    -0.42
    POSITIVE LOGITS
     nahilalakip
    0.85
    //
    0.69
    Naissance
    0.64
    argout
    0.62
    classnames
    0.59
    httphttps
    0.59
    WebServlet
    0.58
    CodeAttribute
    0.58
     AssemblyCompany
    0.57
     StatefulWidget
    0.57
    Act Density 0.160%

    No Known Activations