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

    Neuronpedia

    INDEX
    Explanations

    levels, materials, equation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kao
    0.42
     powy
    0.40
     Garantie
    0.40
     Diese
    0.40
    𝑨
    0.39
     परफेक्ट
    0.38
     aceste
    0.38
     Ao
    0.37
     Là
    0.37
    ßer
    0.37
    POSITIVE LOGITS
     zarówno
    0.36
    及其
    0.35
     अस्तित्व
    0.35
     हमें
    0.35
     conciencia
    0.35
     biocompat
    0.35
    意识
    0.34
    的存在
    0.34
    甚至
    0.34
    衡量
    0.34
    Act Density 0.056%

    No Known Activations