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

    Neuronpedia

    INDEX
    Explanations

    JSON data structures or related syntax elements

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

    POSIX ecosystem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Azevedo
    -0.39
     Hofmann
    -0.36
     Klassen
    -0.36
    ,
    -0.36
    grenzung
    -0.35
     if
    -0.35
    ATIVO
    -0.34
    M
    -0.34
     Persson
    -0.34
     McFadden
    -0.34
    POSITIVE LOGITS
     {...
    2.45
    {...
    2.13
     [...
    0.97
     (...
    0.88
    ([...
    0.79
    MemoryWarning
    0.74
     (...)
    0.73
    (...)
    0.71
     "..."
    0.70
    (...
    0.69
    Act Density 0.001%

    No Known Activations