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

    Neuronpedia

    INDEX
    Explanations

    Tourist locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cs
    -0.06
    'y
    -0.06
     подв
    -0.06
    チェ
    -0.06
     Thinking
    -0.06
     presidential
    -0.06
    _TO
    -0.06
    /he
    -0.06
    categorie
    -0.06
    -fed
    -0.06
    POSITIVE LOGITS
    .Big
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
     proactive
    0.06
    );↵↵↵↵
    0.06
    '},↵
    0.06
    unun
    0.06
     Türkiye
    0.06
    itating
    0.06
    elling
    0.06
     Nokia
    0.06
    Act Density 0.069%

    No Known Activations