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

    Neuronpedia

    INDEX
    Explanations

    text and code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ంబ
    0.35
     只
    0.29
     только
    0.29
     Wyoming
    0.29
     пога
    0.28
     Bolts
    0.28
     Spotify
    0.28
     কয়েক
    0.28
     এটা
    0.27
     eta
    0.27
    POSITIVE LOGITS
     entrenched
    0.36
    ੂ
    0.35
    を購入
    0.31
    Lorsque
    0.30
    宣言
    0.30
    landish
    0.30
    じる
    0.29
     nostrum
    0.29
    continued
    0.28
     приступи
    0.28
    Act Density 0.001%

    No Known Activations