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

    Neuronpedia

    INDEX
    Explanations

    queens and wars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    羊
    0.44
    ಫ
    0.43
    ܕ
    0.39
     알파
    0.38
    德國
    0.38
     অপ্র
    0.38
     soprav
    0.38
    মের
    0.37
    вропей
    0.37
    冧
    0.37
    POSITIVE LOGITS
     Cake
    0.68
     cake
    0.66
    Cake
    0.61
    cake
    0.57
     cakes
    0.56
     Configure
    0.55
     debug
    0.53
     Nottingham
    0.53
     केक
    0.52
    Configure
    0.51
    Act Density 0.001%

    No Known Activations