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

    Neuronpedia

    INDEX
    Explanations

    definitions and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ።
    0.52
    nbs
    0.49
    ។
    0.49
    GeV
    0.48
    最大の
    0.48
     лучших
    0.47
    %。
    0.47
     найбіль
    0.46
     Jazeera
    0.46
    п
    0.45
    POSITIVE LOGITS
    运算符
    0.42
     Biochem
    0.38
     zach
    0.38
     MK
    0.37
     være
    0.37
    可是
    0.37
     Sut
    0.37
     Mutable
    0.37
    ikus
    0.36
     Mark
    0.36
    Act Density 0.003%

    No Known Activations