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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Constantin
    -0.07
    ɹ
    -0.07
    椒
    -0.07
    optic
    -0.07
    created
    -0.07
    oku
    -0.06
    蛟
    -0.06
    一脚
    -0.06
    濯
    -0.06
     cyan
    -0.06
    POSITIVE LOGITS
    𩾌
    0.07
    ointment
    0.07
    &);↵
    0.07
    ="#"><
    0.06
    //(
    0.06
    (custom
    0.06
     Fey
    0.06
     بالإضافة
    0.06
    率为
    0.06
     curse
    0.06
    Act Density 0.013%

    No Known Activations