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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash

    This neuron flags numeric error‐code tokens (e.g. the numbers following “Errno” in exception tracebacks).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    　　　　　
    -0.07
     bribery
    -0.07
    　　　　
    -0.06
    νης
    -0.06
     repairing
    -0.06
    ılır
    -0.06
     Falcon
    -0.06
     комплекс
    -0.06
    ्यवस
    -0.06
    -0.06
    POSITIVE LOGITS
     emojis
    0.06
    useppe
    0.06
     ;;↵
    0.06
     CGContext
    0.06
     найд
    0.06
    ühl
    0.06
     Заг
    0.06
     Touch
    0.06
    _SSL
    0.06
     OSC
    0.06
    Act Density 0.005%

    No Known Activations