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

    Neuronpedia

    INDEX
    Explanations

    unnecessary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enclosed
    -0.07
     setOpen
    -0.07
    const
    -0.07
    转型
    -0.07
    ảnh
    -0.06
    bindValue
    -0.06
    合作
    -0.06
    `='$
    -0.06
     exams
    -0.06
    -Regular
    -0.06
    POSITIVE LOGITS
    inheritdoc
    0.08
    Roy
    0.08
    .defaults
    0.07
     prostituerte
    0.07
     başlat
    0.07
    .book
    0.07
     pratique
    0.07
     impacting
    0.07
    缺席
    0.07
     أيضا
    0.07
    Act Density 0.010%

    No Known Activations