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

    Neuronpedia

    INDEX
    Explanations

    oper

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etus
    -0.07
    igner
    -0.07
    (controller
    -0.07
    LLLL
    -0.07
    AtA
    -0.07
    厘米
    -0.06
    Logged
    -0.06
    ounds
    -0.06
    eday
    -0.06
     taught
    -0.06
    POSITIVE LOGITS
     Hương
    0.08
     blackout
    0.07
     NSError
    0.07
     Sco
    0.07
     ucfirst
    0.07
     temas
    0.07
     IID
    0.07
     milestones
    0.07
    排查
    0.06
    竞争对手
    0.06
    Act Density 0.006%

    No Known Activations