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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron fires on C‐style pointer member accesses using the “->” operator.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    agy
    -0.06
     zipfile
    -0.06
    /assert
    -0.06
    .JMenuItem
    -0.06
    MARY
    -0.06
    енс
    -0.06
    isbn
    -0.06
    .createTextNode
    -0.06
    σή
    -0.06
     crucial
    -0.06
    POSITIVE LOGITS
    orption
    0.07
    development
    0.07
     server
    0.07
     사이트
    0.06
    _RUNNING
    0.06
    GPU
    0.06
    -through
    0.06
    _years
    0.06
     predictors
    0.06
     인터넷
    0.06
    Act Density 0.034%

    No Known Activations