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

    Neuronpedia

    INDEX
    Explanations

    placement or imposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Da
    0.45
    zem
    0.43
    Graphic
    0.41
    Cars
    0.41
    ésil
    0.40
    special
    0.38
    Eng
    0.37
     באמצעות
    0.37
    Sn
    0.37
    zw
    0.37
    POSITIVE LOGITS
     imposed
    0.43
     imposition
    0.40
     impregnation
    0.40
     impregnated
    0.39
     montée
    0.39
     placement
    0.39
     Placement
    0.38
     postav
    0.38
     phd
    0.38
     dino
    0.38
    Act Density 0.000%

    No Known Activations