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

    Neuronpedia

    INDEX
    Explanations

    00

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on the two-character “00” byte token (i.e. the hex value 0x00).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     손을
    -0.07
     Research
    -0.07
     roi
    -0.06
    _peng
    -0.06
     Üst
    -0.06
    }↵↵↵↵↵
    -0.06
     Component
    -0.06
     알
    -0.06
     розрах
    -0.06
    학
    -0.06
    POSITIVE LOGITS
    00
    0.10
     //{
↵
    0.07
    emann
    0.07
    97
    0.07
    ");
    0.07
     err
    0.07
    0.07
    ')
    0.07
    стра
    0.07
    YNC
    0.06
    Act Density 0.018%

    No Known Activations