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

    Neuronpedia

    INDEX
    Explanations

    say "cart"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cuc
    0.48
     KC
    0.47
     ку
    0.45
    الك
    0.43
    ку
    0.41
     ค
    0.41
    kc
    0.41
    КУ
    0.40
     Kün
    0.40
    یو
    0.40
    POSITIVE LOGITS
     ca
    0.53
     cart
    0.52
     Ca
    0.51
    cart
    0.51
     caro
    0.48
     Cart
    0.47
     caer
    0.46
     CART
    0.46
    ca
    0.46
     cat
    0.45
    Act Density 0.001%

    No Known Activations