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

    Neuronpedia

    INDEX
    Explanations

    problems and issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وغ
    -0.07
     собствен
    -0.06
     جمعیت
    -0.06
    ！”↵↵
    -0.06
    —in
    -0.06
    .and
    -0.06
    -0.06
     gözlem
    -0.06
     làng
    -0.06
     Joshua
    -0.06
    POSITIVE LOGITS
    .ham
    0.07
    emem
    0.06
    chied
    0.06
     McD
    0.06
    option
    0.06
     opting
    0.06
     hodiny
    0.06
     competitive
    0.06
     inherently
    0.06
    選
    0.06
    Act Density 0.035%
    No Known Activations