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

    Neuronpedia

    INDEX
    Explanations

    help us diagnose you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doxycycline
    1.52
     unable
    1.50
     Jenis
    1.47
    д
    1.46
     étrangères
    1.45
    岖
    1.45
    ي
    1.45
    Gonz
    1.44
     Lessor
    1.42
     Unable
    1.40
    POSITIVE LOGITS
     ích
    1.62
    ం
    1.60
     đỡ
    1.50
    ю
    1.42
    о
    1.38
    ление
    1.38
    ok
    1.34
    othesis
    1.34
    प्तान
    1.33
    ная
    1.31
    Act Density 0.283%

    No Known Activations