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

    Neuronpedia

    INDEX
    Explanations

    car compounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deliveries
    0.71
     sw
    0.68
     neque
    0.68
     blinds
    0.67
     swipes
    0.67
     Nxc
    0.67
     swipe
    0.65
     शता
    0.65
     السب
    0.65
    pool
    0.65
    POSITIVE LOGITS
     box
    0.75
    בו
    0.70
    بو
    0.70
    Box
    0.70
    Cin
    0.69
     cinética
    0.69
    box
    0.68
    Bo
    0.67
    BO
    0.67
    bons
    0.67
    Act Density 0.004%

    No Known Activations