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

    Neuronpedia

    INDEX
    Explanations

    references to abstract concepts or technical terms

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

    text that looks like code or formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onCreateView
    -0.45
    //
    -0.36
    ardo
    -0.31
    TagMode
    -0.31
     AssemblyVersion
    -0.30
    zionalità
    -0.30
    <?
    -0.30
    sketch
    -0.29
     OK
    -0.29
    ok
    -0.29
    POSITIVE LOGITS
     OMITBAD
    1.00
    Tikang
    0.99
    verwijspagina
    0.75
     resourceCulture
    0.72
     <<<<<<<<<<<<<<
    0.71
    Personendaten
    0.68
     ujednoznacz
    0.64
    delwed
    0.63
    principalTable
    0.63
     disambiguazione
    0.62
    Act Density 0.005%

    No Known Activations