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

    Neuronpedia

    INDEX
    Explanations

    print

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VN
    -0.07
     burdens
    -0.06
     headaches
    -0.06
    jn
    -0.06
    ázev
    -0.06
    ildi
    -0.06
    уют
    -0.06
    isos
    -0.06
    +l
    -0.06
     Mir
    -0.06
    POSITIVE LOGITS
    ステム
    0.07
    .Here
    0.06
     femin
    0.06
     문
    0.06
     stringstream
    0.06
    dling
    0.06
     ابتدا
    0.06
     اهمیت
    0.06
    равиль
    0.06
    ンド
    0.06
    Act Density 0.016%

    No Known Activations