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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seasoned
    -0.07
    务必
    -0.07
    题目
    -0.07
    灼
    -0.06
    멸
    -0.06
     zum
    -0.06
     seen
    -0.06
    商品
    -0.06
    EIF
    -0.06
     bother
    -0.06
    POSITIVE LOGITS
    כשיו
    0.07
    �
    0.07
    -post
    0.07
     Cas
    0.06
    Effects
    0.06
     tenga
    0.06
     Ratio
    0.06
    posición
    0.06
    .curve
    0.06
     ardından
    0.06
    Act Density 0.006%

    No Known Activations