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

    Neuronpedia

    INDEX
    Explanations

    place, placing, placed, placement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ინი
    0.40
     применения
    0.38
     الشر
    0.38
     sensations
    0.36
     случа
    0.35
     मनाया
    0.35
    ुप
    0.35
    roj
    0.35
    cic
    0.35
     चला
    0.35
    POSITIVE LOGITS
     Placing
    0.96
     placed
    0.91
     Placement
    0.89
     placing
    0.86
     placement
    0.84
    Placement
    0.81
    placed
    0.80
     placés
    0.80
     umíst
    0.77
     emphasis
    0.76
    Act Density 0.018%

    No Known Activations