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

    Neuronpedia

    INDEX
    Explanations

    URLs linking to model websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    胞
    0.47
     hữu
    0.39
     berjudul
    0.39
    secure
    0.38
     credible
    0.38
     deporte
    0.38
    字体
    0.37
     الموجود
    0.37
     monotony
    0.37
     sport
    0.37
    POSITIVE LOGITS
     jett
    0.45
     Ether
    0.40
     Hành
    0.39
     Laver
    0.39
    ENTER
    0.38
    よ
    0.38
    فت
    0.38
    vection
    0.37
     Wynne
    0.37
    cmake
    0.37
    Act Density 0.014%

    No Known Activations