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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rades
    -0.07
    ildiği
    -0.06
    URLOPT
    -0.06
     bulls
    -0.06
    "...
    -0.06
    थ
    -0.06
     outro
    -0.06
    ู้
    -0.06
    ỗ
    -0.06
     './
    -0.06
    POSITIVE LOGITS
    addir
    0.07
     inn
    0.06
    Datos
    0.06
    (last
    0.06
     图
    0.06
     Jenny
    0.06
    复
    0.06
    ett
    0.06
     그녀
    0.06
     opi
    0.06
    Act Density 0.000%

    No Known Activations