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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ។↵↵
    -0.11
     ۔↵↵
    -0.11
     كسارة
    -0.11
     אויפ
    -0.11
     zogenaamde
    -0.11
     ნების
    -0.10
    .«↵↵
    -0.10
     ».↵↵
    -0.10
    。」↵↵
    -0.10
     assigi
    -0.10
    POSITIVE LOGITS
    ”和
    0.13
    했고
    0.13
     आणि
    0.12
     மற்றும்
    0.11
    》和
    0.11
     和
    0.11
    、
    0.11
     और
    0.11
     and
    0.11
     ਅਤੇ
    0.11
    Act Density 0.107%

    No Known Activations