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

    Neuronpedia

    INDEX
    Explanations

    Code/non-sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    intosh
    -0.06
     gp
    -0.06
    .sc
    -0.06
    ieres
    -0.06
    _Se
    -0.06
    ostat
    -0.06
    部
    -0.06
     Xi
    -0.06
     dân
    -0.06
     Illinois
    -0.06
    POSITIVE LOGITS
    Warnings
    0.07
    ्वय
    0.07
     xuất
    0.07
    .assertIsNot
    0.07
     exe
    0.06
     ash
    0.06
    ③
    0.06
     freezing
    0.06
    裏
    0.06
     dikkat
    0.06
    Act Density 0.000%

    No Known Activations