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

    Neuronpedia

    INDEX
    Explanations

    programming-related function declarations and method definitions

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

    testing method calls and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.66
     betweenstory
    -0.63
    #+#
    -0.50
     Мексичка
    -0.50
     ExecuteAsync
    -0.48
    Personendaten
    -0.47
     PeEnEo
    -0.47
     almohada
    -0.45
    OGND
    -0.44
     wikipagina
    -0.43
    POSITIVE LOGITS
    AccessorTable
    0.60
     تضيفلها
    0.53
    contentLoaded
    0.44
    oneofs
    0.42
    ‍♂
    0.39
    ‍♂️
    0.38
    felves
    0.38
    saraba
    0.38
    ‍♀
    0.38
    UrlResolution
    0.37
    Act Density 0.049%

    No Known Activations