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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     National
    -0.07
     הר
    -0.07
    (stats
    -0.07
    ması
    -0.07
     Penis
    -0.07
     nonlinear
    -0.07
    จ
    -0.07
     באופן
    -0.07
     Exercises
    -0.07
    esimal
    -0.06
    POSITIVE LOGITS
    揩
    0.07
    辒
    0.06
     hắn
    0.06
    uC
    0.06
    年人
    0.06
    ter
    0.06
     Dorm
    0.06
    客人
    0.06
    Choice
    0.06
     amat
    0.06
    Act Density 0.057%

    No Known Activations