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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    春季
    -0.09
    ATEST
    -0.07
    Quiz
    -0.07
             ↵
    -0.07
    {↵↵
    -0.07
     Skill
    -0.07
     [...]↵↵
    -0.07
     Wid
    -0.07
     tegen
    -0.07
    .Min
    -0.07
    POSITIVE LOGITS
    .assignment
    0.07
     רבה
    0.07
    娛樂
    0.07
     thỏa
    0.07
    不变
    0.07
    ecret
    0.07
     orgy
    0.07
    úb
    0.07
    ,application
    0.07
     thoải
    0.07
    Act Density 0.078%

    No Known Activations