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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gear
    -0.06
     Corner
    -0.06
     Moj
    -0.06
     وزارت
    -0.06
     شر
    -0.06
     Brothers
    -0.06
    additional
    -0.06
     //--------------------------------
    -0.06
     '');↵
    -0.06
    Community
    -0.06
    POSITIVE LOGITS
    ！！
    0.07
     하고
    0.07
    ër
    0.07
    _v
    0.07
    ΑΡ
    0.07
     puede
    0.07
     aunque
    0.06
    μέ
    0.06
    .CompilerServices
    0.06
    하고
    0.06
    Act Density 0.003%

    No Known Activations