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

    Neuronpedia

    INDEX
    Explanations

    factory pattern, additive manufacturing, Romanov, experiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ल
    0.52
     l
    0.47
    ा
    0.46
    l
    0.45
     fester
    0.44
     glomerul
    0.43
     lys
    0.43
    マスター
    0.42
    喺
    0.42
    ಲ
    0.42
    POSITIVE LOGITS
    owych
    0.49
    owią
    0.46
    浓度
    0.45
     produktów
    0.44
    运算符
    0.44
    轻松
    0.44
    ισμού
    0.44
    owym
    0.43
    owego
    0.43
    owanie
    0.42
    Act Density 0.003%

    No Known Activations