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

    Neuronpedia

    INDEX
    Explanations

    Stack traces and code

    np_max-act · gemini-2.0-flash

    The neuron activates on Java exception stack‐trace elements, i.e. class and method names appearing in error backtraces.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     eles
    -0.07
     furry
    -0.06
    .fp
    -0.06
    ุณ
    -0.06
     그래
    -0.06
     domů
    -0.06
    foundland
    -0.06
    _relation
    -0.06
    isc
    -0.06
    .cn
    -0.06
    POSITIVE LOGITS
     dumpsters
    0.08
     tím
    0.08
     swell
    0.07
    _twitter
    0.07
    Creator
    0.07
     amongst
    0.06
    .Closed
    0.06
    (Key
    0.06
     MOV
    0.06
    _CREATE
    0.06
    Act Density 0.032%

    No Known Activations