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

    Neuronpedia

    INDEX
    Explanations

    sets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .isHidden
    -0.08
    DATED
    -0.07
     Ş
    -0.06
     Đây
    -0.06
     vydání
    -0.06
    ','$
    -0.06
                ↵↵
    -0.06
    .squareup
    -0.06
     창
    -0.06
    него
    -0.06
    POSITIVE LOGITS
     Kelley
    0.06
    vrolet
    0.06
     blazing
    0.06
    金
    0.06
     UD
    0.06
    优势
    0.06
     半
    0.06
    贴
    0.06
     Ges
    0.06
    ských
    0.06
    Act Density 0.000%

    No Known Activations