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

    Neuronpedia

    INDEX
    Explanations

    2023-10-26

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sons
    0.36
    iments
    0.36
    める
    0.36
     adına
    0.34
    IOS
    0.34
     soaps
    0.34
     dozens
    0.33
    ப்பினர்
    0.33
     করণ
    0.33
    nok
    0.32
    POSITIVE LOGITS
    🫶
    0.33
     Dang
    0.33
     hipótes
    0.32
    <unused100>
    0.32
     எச்ச
    0.31
    لة
    0.31
     সম্প্রতি
    0.31
     bekommt
    0.31
    intermediate
    0.30
    Dang
    0.30
    Act Density 0.018%

    No Known Activations