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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to type definitions and function declarations

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

    function return types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.85
    Personensuche
    -0.77
    хьтан
    -0.76
    帖最后由
    -0.75
    Cyfarwyddwr
    -0.75
    ьаж
    -0.74
    parsedMessage
    -0.72
    клопе
    -0.71
    IntOverflow
    -0.69
     חיצוניים
    -0.69
    POSITIVE LOGITS
    ))),
    0.40
    ))).
    0.40
    ])),
    0.36
     “
    0.36
     "
    0.35
     thus
    0.33
     pet
    0.33
    ))))
    0.31
    )),
    0.31
     Mr
    0.30
    Act Density 0.265%

    No Known Activations