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

    Neuronpedia

    INDEX
    Explanations

    placement and orientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समृद्ध
    0.75
     жан
    0.73
    masının
    0.72
     sadr
    0.72
    forgettable
    0.71
     ক্যাথ
    0.71
     sadrž
    0.71
     membawa
    0.71
    ENDAR
    0.70
    engkap
    0.70
    POSITIVE LOGITS
     positioning
    1.90
     angles
    1.82
     angle
    1.76
     placement
    1.76
     alignment
    1.67
     spacing
    1.65
     Positioning
    1.62
     angled
    1.58
     positions
    1.57
     position
    1.56
    Act Density 0.468%

    No Known Activations