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

    Neuronpedia

    INDEX
    Explanations

    structural elements or notations commonly used in mathematical or programming syntax

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

    Closing brackets

    np_acts-logits-general · gemini-2.0-flash

    closing brackets and delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fé
    -0.74
     pedals
    -0.71
     Crocker
    -0.71
     trin
    -0.68
    PageIndex
    -0.68
     Goodwin
    -0.67
     GTR
    -0.66
     Aze
    -0.66
     Gund
    -0.66
     pst
    -0.65
    POSITIVE LOGITS
    }]
    1.00
    _]
    0.96
    })]
    0.91
    \"]
    0.90
    ]]
    0.90
    ″]
    0.89
     ]
    0.89
    :]
    0.86
    ]>
    0.82
    .]
    0.82
    Act Density 0.650%

    No Known Activations