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

    Neuronpedia

    INDEX
    Explanations

    German text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tw
    0.64
    Kam
    0.63
    గా
    0.62
    Tim
    0.59
    Fro
    0.58
     doet
    0.58
    Bold
    0.57
    cami
    0.57
    ูน
    0.57
    dml
    0.56
    POSITIVE LOGITS
     குறிப்பிட
    0.69
     п
    0.65
    េរ
    0.64
     सर्वोच्च
    0.63
     ઓળ
    0.63
     noise
    0.63
     остаются
    0.62
    输出
    0.61
     ব্যতীত
    0.61
     মুজিবর
    0.61
    Act Density 0.043%

    No Known Activations