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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literal tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     انگ
    -0.07
     spindle
    -0.07
     hava
    -0.06
     事
    -0.06
    cím
    -0.06
     halk
    -0.06
     landfill
    -0.06
    clientId
    -0.06
     SERIAL
    -0.06
     oppon
    -0.06
    POSITIVE LOGITS
     confirming
    0.06
    mates
    0.06
    狀
    0.06
    оки
    0.06
    cover
    0.06
    dice
    0.06
    Flexible
    0.06
    ,copy
    0.06
    @nate
    0.06
     виник
    0.06
    Act Density 0.023%

    No Known Activations