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

    Neuronpedia

    INDEX
    Explanations

    code coordinates

    np_max-act · gemini-2.0-flash

    This neuron detects Python list‐slicing expressions, especially the “i : i + n” pattern used for splitting a list into sublists.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    GORITHM
    -0.07
     salesman
    -0.07
     openings
    -0.06
    ocaly
    -0.06
     audio
    -0.06
     intest
    -0.06
     NSStringFromClass
    -0.06
    	writer
    -0.06
    선을
    -0.06
    测
    -0.06
    POSITIVE LOGITS
    .low
    0.07
    Dat
    0.06
     Secretary
    0.06
     جان
    0.06
     varied
    0.06
     deprived
    0.06
    });↵↵↵
    0.06
    257
    0.06
     Lottery
    0.06
    Expense
    0.06
    Act Density 0.066%

    No Known Activations