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

    Neuronpedia

    INDEX
    Explanations

    most other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bt
    0.38
     franch
    0.38
    financed
    0.37
    BT
    0.36
    ywidual
    0.35
    forgettable
    0.35
    ನಿ
    0.35
     جانب
    0.34
    VENUE
    0.34
     सुप्रीम
    0.34
    POSITIVE LOGITS
     غال
    0.42
     větš
    0.41
     대부분
    0.41
     большинстве
    0.41
    غال
    0.40
     Auger
    0.40
     عادة
    0.40
     ছুই
    0.39
     большинства
    0.39
     большинство
    0.39
    Act Density 0.002%

    No Known Activations