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

    Neuronpedia

    INDEX
    Explanations

    translate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مردم
    -0.07
    未来
    -0.07
    /token
    -0.07
     pestic
    -0.07
     muscle
    -0.07
     Fonts
    -0.06
    GroupBox
    -0.06
     verst
    -0.06
    -Smith
    -0.06
     услуг
    -0.06
    POSITIVE LOGITS
     gross
    0.07
     сл
    0.07
    #ifndef
    0.06
     mates
    0.06
     Moh
    0.06
     Sol
    0.06
     새로운
    0.06
                ↵
    0.06
    >\<
    0.06
     joked
    0.06
    Act Density 0.020%

    No Known Activations