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

    Neuronpedia

    INDEX
    Explanations

    picking pockets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     violencia
    0.42
     Sada
    0.41
     Visualize
    0.40
     violence
    0.40
     lote
    0.38
     Gewalt
    0.38
     visualizing
    0.38
     शत्रु
    0.38
     Violence
    0.37
    স্ত্র
    0.37
    POSITIVE LOGITS
     pick
    1.23
    pick
    1.20
    Pick
    1.09
     Pick
    1.07
     PICK
    0.93
    PICK
    0.92
     picked
    0.84
    picking
    0.80
     picks
    0.79
    picker
    0.78
    Act Density 0.011%

    No Known Activations