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

    Neuronpedia

    INDEX
    Explanations

    interested in information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.64
    ：
    0.54
    L
    0.53
    </li>
    0.52
    itting
    0.51
    '।
    0.50
    位置
    0.49
    ），
    0.49
    használ
    0.48
     ଭ
    0.48
    POSITIVE LOGITS
     interest
    0.91
     interested
    0.91
     interess
    0.86
     관심
    0.82
     INTEREST
    0.82
     minat
    0.81
     interesse
    0.80
     interests
    0.77
     Interest
    0.77
     interes
    0.77
    Act Density 0.047%

    No Known Activations