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

    Neuronpedia

    INDEX
    Explanations

    instances of nested function or method calls in code

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

    tokens starting with __

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marín
    -0.47
    }})
    -0.47
    }])
    -0.44
     }}$.
    -0.44
    %}
    -0.43
    })).
    -0.42
    '))
    -0.42
     Zink
    -0.42
     })
    -0.41
    ')))
    -0.40
    POSITIVE LOGITS
    (__
    2.70
     (__
    1.86
    [__
    1.27
     (!__
    1.11
    (___
    1.09
    (!__
    1.08
    (_
    1.07
     *__
    0.99
    ::__
    0.94
    ($__
    0.92
    Act Density 0.018%

    No Known Activations