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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tick
    -0.07
     الأم
    -0.06
     uw
    -0.06
     zf
    -0.06
    indered
    -0.06
    stag
    -0.06
     검
    -0.06
    ух
    -0.06
     [<
    -0.06
     ense
    -0.06
    POSITIVE LOGITS
    мага
    0.07
    Cursor
    0.07
    ै।
    0.06
     Giám
    0.06
    мини
    0.06
    "]))↵
    0.06
    ouched
    0.06
     amusing
    0.06
     halted
    0.06
    里
    0.06
    Act Density 0.000%

    No Known Activations