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

    Neuronpedia

    INDEX
    Explanations

    closing brackets or parentheses in mathematical or programming contexts

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

    closing square bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isSuccessful
    -0.48
     Vann
    -0.42
     Vogel
    -0.40
     Governor
    -0.40
    cida
    -0.40
    -0.39
    حياتها
    -0.39
     sinh
    -0.39
     umas
    -0.39
     Tos
    -0.38
    POSITIVE LOGITS
     ...]
    0.68
    ...]
    0.67
    ?]
    0.67
    …]
    0.66
    ]]]
    0.66
     "]
    0.65
    []]
    0.64
    ]][
    0.64
     ]
    0.64
    ]
    0.63
    Act Density 0.418%

    No Known Activations