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

    Neuronpedia

    INDEX
    Explanations

    要

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     firearm
    -0.07
    状態
    -0.07
    ryption
    -0.06
    fleet
    -0.06
    _L
    -0.06
     cultured
    -0.06
    etin
    -0.06
     firearms
    -0.06
    [String
    -0.06
     slices
    -0.06
    POSITIVE LOGITS
     мік
    0.07
    /question
    0.07
     Judith
    0.07
    <List
    0.06
     yılda
    0.06
     oppose
    0.06
     SKIP
    0.06
     antagon
    0.06
     παρ
    0.06
    OfYear
    0.06
    Act Density 0.002%

    No Known Activations