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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jo
    0.42
     produktu
    0.40
    beel
    0.40
    vodu
    0.38
    woch
    0.37
    compressed
    0.36
     produit
    0.35
     photographie
    0.35
    "};
    0.35
    ヴォ
    0.35
    POSITIVE LOGITS
    詛
    0.40
    诅
    0.38
    絫
    0.38
    ക്കുറിച്ച
    0.37
    実装
    0.37
    äume
    0.37
    沿
    0.37
     при
    0.36
    телей
    0.36
    制度
    0.36
    Act Density 0.007%

    No Known Activations