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

    Neuronpedia

    INDEX
    Explanations

    don't let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    桕
    -0.08
     시간
    -0.07
     vetor
    -0.07
    <long
    -0.07
     axe
    -0.07
     масло
    -0.07
    terdam
    -0.07
    盘点
    -0.07
    ورد
    -0.07
     PIXEL
    -0.06
    POSITIVE LOGITS
    ouncements
    0.07
    Notes
    0.07
     stray
    0.07
    Disclaimer
    0.07
     casualty
    0.07
    lobs
    0.07
     injuring
    0.07
    Attributes
    0.07
     Quote
    0.06
     notes
    0.06
    Act Density 0.031%

    No Known Activations