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

    Neuronpedia

    INDEX
    Explanations

    motivational quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     അട
    -0.08
    /sample
    -0.08
     يك
    -0.07
     penser
    -0.07
     dacht
    -0.07
     imaginable
    -0.07
     princ
    -0.07
     vac
    -0.07
     parlamentar
    -0.07
     Сам
    -0.07
    POSITIVE LOGITS
    侧
    0.07
     mucha
    0.07
    .DAO
    0.07
     robustness
    0.07
     sometime
    0.07
     executives
    0.07
    fstream
    0.07
     scipy
    0.07
     Money
    0.07
    。我
    0.07
    Act Density 0.020%

    No Known Activations