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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CX
    -0.08
     jumper
    -0.07
     ostatní
    -0.06
     replicated
    -0.06
     Stadt
    -0.06
     آور
    -0.06
    ucose
    -0.06
    )]
↵
    -0.06
     lz
    -0.06
     grac
    -0.06
    POSITIVE LOGITS
     مس
    0.06
    身
    0.06
    IODevice
    0.06
     الشيخ
    0.06
    阳城
    0.06
     AlertDialog
    0.06
     CALL
    0.06
    ندان
    0.06
    (PDO
    0.06
     Imagine
    0.06
    Act Density 0.013%

    No Known Activations