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

    Neuronpedia

    INDEX
    Explanations

    non-english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    अ
    -0.08
     परिस
    -0.07
    Introduce
    -0.07
     ubiquitous
    -0.07
    Puzzle
    -0.07
     isn't
    -0.07
     pemb
    -0.07
    /D
    -0.07
     disposição
    -0.07
    rà
    -0.07
    POSITIVE LOGITS
     Rouge
    0.08
    ére
    0.08
     circumstances
    0.08
     Ayur
    0.08
    atomic
    0.08
     west
    0.08
     Sheng
    0.08
     bawah
    0.08
    amagitan
    0.07
     Brighton
    0.07
    Act Density 0.055%

    No Known Activations