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

    Neuronpedia

    INDEX
    Explanations

    Services

    np_max-act · gemini-2.0-flash

    The neuron flags code tokens related to UI dialog classes—i.e. any occurrence of “Dialog” in class or import names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     stellt
    -0.06
     smiles
    -0.06
     -------------
    -0.06
     Supports
    -0.06
     horizon
    -0.06
     thus
    -0.06
    ilden
    -0.06
    うち
    -0.06
     rich
    -0.06
    -holder
    -0.06
    POSITIVE LOGITS
    _gas
    0.07
    śnie
    0.07
    ось
    0.06
    &);↵↵
    0.06
     StatelessWidget
    0.06
     quá
    0.06
     QImage
    0.06
    แสง
    0.06
    dots
    0.06
    nač
    0.06
    Act Density 0.124%

    No Known Activations