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

    Neuronpedia

    INDEX
    Explanations

    references to coding functions and programming logic

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

    Tokens preceding "processed", "design", or "collections"

    np_acts-logits-general · gemini-2.0-flash

    more conveniently processed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Offisielt
    -0.61
     voici
    -0.59
    <?
    -0.59
     createState
    -0.55
     ""],
    -0.54
     BoxFit
    -0.54
    enumii
    -0.54
     Jefus
    -0.54
     Monfieur
    -0.54
     Theſe
    -0.54
    POSITIVE LOGITS
     easier
    0.72
     Easier
    0.69
    Easier
    0.68
    easier
    0.64
    eschön
    0.55
    RegressionTest
    0.51
     AssemblyCulture
    0.51
    ppsala
    0.51
     mudah
    0.49
     simpler
    0.49
    Act Density 0.768%

    No Known Activations