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

    Neuronpedia

    INDEX
    Explanations

    occurrences of print statements in code

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

    Characters after `printf` and format specifiers

    np_acts-logits-general · gemini-2.0-flash

    printf/fprintf calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.72
    SequentialGroup
    -0.69
    сылкі
    -0.68
     disambiguazione
    -0.68
     <>",
    -0.63
    COUVER
    -0.59
     snippetHide
    -0.57
    verwijspagina
    -0.56
     שוליים
    -0.54
    ictwo
    -0.53
    POSITIVE LOGITS
     "%
    0.98
    ("%
    0.97
    "%
    0.85
    ,"%
    0.73
     '%
    0.69
    '%
    0.69
     ("%
    0.69
    ="%
    0.67
    ("%.
    0.65
    _%
    0.63
    Act Density 0.066%

    No Known Activations