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

    Neuronpedia

    INDEX
    Explanations

    SENSOR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beams
    -0.07
    DIM
    -0.07
    _fw
    -0.06
     overnight
    -0.06
     wholesale
    -0.06
     пров
    -0.06
     toplam
    -0.06
     Pr
    -0.06
     удал
    -0.06
    .dist
    -0.06
    POSITIVE LOGITS
    >').
    0.07
    ่ใช
    0.07
     '{@
    0.07
     세상
    0.07
     AUTHOR
    0.06
    The
    0.06
    ENTITY
    0.06
     Chef
    0.06
    τύ
    0.06
    Environmental
    0.06
    Act Density 0.386%

    No Known Activations