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

    Neuronpedia

    INDEX
    Explanations

    mathematical sequences

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric tokens, especially multi‐digit numbers (i.e. it detects number strings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _debug
    -0.07
    833
    -0.07
     config
    -0.07
    ItemImage
    -0.06
     Bose
    -0.06
    frame
    -0.06
    브
    -0.06
     WAN
    -0.06
    _red
    -0.06
    _configuration
    -0.06
    POSITIVE LOGITS
     shootings
    0.07
     clash
    0.07
    ี้↵
    0.06
     estates
    0.06
     Birthday
    0.06
    ());//
    0.06
     punish
    0.06
    名無しさん
    0.06
     sla
    0.06
    ANTI
    0.06
    Act Density 0.007%

    No Known Activations