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

    Neuronpedia

    INDEX
    Explanations

    moving physical objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🖋
    0.41
    消化
    0.41
     ആരാധ
    0.38
    Nonce
    0.38
     dt
    0.37
    ्यता
    0.37
    𒁺
    0.37
    ងឺ
    0.37
    音声
    0.37
    భి
    0.36
    POSITIVE LOGITS
     transporting
    0.92
     movers
    0.91
    搬
    0.85
     mover
    0.84
     transportar
    0.81
     транспорти
    0.80
     Movers
    0.79
     hauling
    0.79
     transported
    0.76
    transport
    0.75
    Act Density 0.195%

    No Known Activations