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

    Neuronpedia

    INDEX
    Explanations

    Order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िथ
    -0.06
    Processing
    -0.06
    نامج
    -0.06
     pipe
    -0.06
    pret
    -0.06
    anlar
    -0.06
     Thatcher
    -0.06
    喔
    -0.06
     Polo
    -0.06
     whatsoever
    -0.06
    POSITIVE LOGITS
     sö
    0.07
     داخلی
    0.07
    атегор
    0.06
    .login
    0.06
     tactical
    0.06
     undisclosed
    0.06
    امت
    0.06
    logic
    0.06
    _GF
    0.06
     sı
    0.06
    Act Density 0.019%

    No Known Activations