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

    Neuronpedia

    INDEX
    Explanations

    There

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')↵↵↵↵
    -0.07
    арів
    -0.07
    ')↵↵↵
    -0.06
     f
    -0.06
    '↵↵↵
    -0.06
     tp
    -0.06
    '])↵↵↵
    -0.06
     worrying
    -0.06
     ale
    -0.06
    ↵↵↵
    -0.06
    POSITIVE LOGITS
     Cait
    0.07
     免
    0.07
     Kürt
    0.07
     cashier
    0.06
     Raqqa
    0.06
     bureaucr
    0.06
    CppCodeGenWriteBarrier
    0.06
     escal
    0.06
     ευ
    0.06
     cải
    0.06
    Act Density 0.928%

    No Known Activations