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

    Neuronpedia

    INDEX
    Explanations

    script writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     민주
    -0.09
     demuestra
    -0.09
    dem
    -0.09
    Dem
    -0.09
    ેલી
    -0.08
    _dem
    -0.08
     democrática
    -0.08
     democracia
    -0.08
     Democracy
    -0.08
     demonstra
    -0.08
    POSITIVE LOGITS
    标题
    0.09
     concise
    0.09
     पश
    0.08
    以下
    0.08
     Asp
    0.08
     headings
    0.08
    正文
    0.08
     noirs
    0.08
    首先
    0.07
     शव
    0.07
    Act Density 0.081%

    No Known Activations