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

    Neuronpedia

    INDEX
    Explanations

    Technical and explanatory writing

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens containing decimal points (floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     окон
    -0.06
     facilities
    -0.06
    afone
    -0.06
     defendant
    -0.06
     �
    -0.06
    SEQ
    -0.06
     Kathryn
    -0.06
     citiz
    -0.06
    NotNil
    -0.06
    Within
    -0.06
    POSITIVE LOGITS
     dut
    0.07
    687
    0.07
     организ
    0.06
     Rifle
    0.06
     clearfix
    0.06
     Attribute
    0.06
    Tooltip
    0.06
    _PWR
    0.06
     toile
    0.06
    .cf
    0.06
    Act Density 0.014%

    No Known Activations