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

    Neuronpedia

    INDEX
    Explanations

    asking questions and seeking access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﾚ
    0.45
     resumed
    0.43
    %");
    0.43
    かしい
    0.42
    REX
    0.42
    0
    0.42
    ᱘
    0.42
    IAN
    0.41
    zantine
    0.41
    عة
    0.41
    POSITIVE LOGITS
     foliis
    0.44
     Daniel
    0.44
     Wals
    0.44
     zarządz
    0.44
     where
    0.41
    िट
    0.41
     Kad
    0.41
    ن
    0.41
     такая
    0.41
     ilaç
    0.40
    Act Density 0.004%

    No Known Activations