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

    Neuronpedia

    INDEX
    Explanations

    code structures and versioning information

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

    version numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InteropServices
    -0.40
    ]")]
    -0.36
    '))
    -0.35
    ].)
    -0.35
    %',
    -0.35
    ")));
    -0.35
    "])
    -0.34
    setHas
    -0.34
     crit
    -0.33
    '])
    -0.33
    POSITIVE LOGITS
     defaultstate
    0.61
     meille
    0.54
     tensão
    0.52
     zimowa
    0.50
     indipendente
    0.50
     akcji
    0.50
    writerow
    0.50
     wijze
    0.50
     agência
    0.50
     Grüsse
    0.49
    Act Density 0.125%

    No Known Activations