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

    Neuronpedia

    INDEX
    Explanations

    exploring different aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ères
    0.49
    ция
    0.49
     was
    0.49
     szak
    0.49
     s
    0.49
    <0xBE>
    0.48
     gepub
    0.47
     představ
    0.46
     ➤
    0.46
     تھا۔
    0.45
    POSITIVE LOGITS
    al
    0.64
    t
    0.59
    ין
    0.56
    p
    0.52
    ak
    0.49
     wrongfully
    0.47
    lifting
    0.47
    ק
    0.47
     रवाना
    0.46
     समझे
    0.45
    Act Density 0.247%

    No Known Activations