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 floating‐point numeric literals in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wastewater
    -0.08
     commerce
    -0.08
     Joey
    -0.07
     klid
    -0.06
    _START
    -0.06
    _sound
    -0.06
     believed
    -0.06
     ladder
    -0.06
     eighth
    -0.06
     پیام
    -0.06
    POSITIVE LOGITS
    생활
    0.06
    DEN
    0.06
    WARD
    0.06
    losed
    0.06
    regon
    0.06
    쇼
    0.06
    NetBar
    0.06
    ocomplete
    0.06
     üzerinden
    0.06
    快速
    0.06
    Act Density 0.040%

    No Known Activations