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

    Neuronpedia

    INDEX
    Explanations

    step by step instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    btnInventory
    0.53
    ρούν
    0.51
     néanmoins
    0.49
     Còn
    0.47
    াদন
    0.46
    ሉም
    0.46
     cabinetry
    0.46
    </bbox>
    0.46
     agribusiness
    0.45
     这些
    0.45
    POSITIVE LOGITS
    first
    0.69
     first
    0.65
     primero
    0.57
    we
    0.55
    A
    0.54
    ch
    0.52
    首先
    0.52
    v
    0.52
    check
    0.52
    find
    0.49
    Act Density 0.184%

    No Known Activations