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

    Neuronpedia

    INDEX
    Explanations

    contents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ضان
    -0.06
     coats
    -0.06
    แนะนำ
    -0.06
    üsü
    -0.06
    گي
    -0.05
     xuất
    -0.05
     Space
    -0.05
    iseum
    -0.05
    롯
    -0.05
    uur
    -0.05
    POSITIVE LOGITS
     христи
    0.07
     проз
    0.07
    predictions
    0.06
     tempt
    0.06
     flatt
    0.06
    //$
    0.06
    cause
    0.06
     arous
    0.06
    *',
    0.06
     тро
    0.06
    Act Density 0.017%

    No Known Activations