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

    Neuronpedia

    INDEX
    Explanations

    viewing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jc
    -0.07
    /S
    -0.07
    iddle
    -0.06
    ฃ
    -0.06
    ↵↵    ↵
    -0.06
    ង
    -0.06
     yielding
    -0.06
    来找
    -0.06
     exerc
    -0.06
     Beard
    -0.06
    POSITIVE LOGITS
     فكرة
    0.07
    贯穿
    0.07
     hadn
    0.07
     pca
    0.07
    若您
    0.07
    (nullable
    0.07
    原本
    0.07
     actor
    0.07
    .Transactional
    0.06
     rarity
    0.06
    Act Density 0.021%

    No Known Activations