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

    Neuronpedia

    INDEX
    Explanations

    function calls or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    調理
    0.50
    AMINATION
    0.49
    持續
    0.48
    代謝
    0.48
     husbandry
    0.47
    ARTER
    0.47
    RELATES
    0.46
     revitalization
    0.46
    物質
    0.46
    營
    0.46
    POSITIVE LOGITS
    ()
    0.74
    ().
    0.65
     std
    0.64
     `
    0.64
     DataFrame
    0.63
     调用
    0.62
     JSON
    0.61
     =>
    0.60
     !
    0.60
     regex
    0.60
    Act Density 0.005%

    No Known Activations