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

    Neuronpedia

    INDEX
    Explanations

    words starting with can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kunna
    1.35
    ang
    1.05
     вот
    1.01
     والر
    1.00
    gegen
    0.97
    గల
    0.95
    gada
    0.95
     podendo
    0.91
    ๊ก
    0.88
    舱
    0.88
    POSITIVE LOGITS
     hende
    1.31
     ∣
    1.25
    istered
    1.24
    isations
    1.22
    ADIAN
    1.20
    vasser
    1.18
    ્રોલ
    1.17
     sativa
    1.17
    iope
    1.16
    ྷ
    1.16
    Act Density 0.079%

    No Known Activations