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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    κος
    -0.07
     işte
    -0.07
    881
    -0.07
    王
    -0.06
     containing
    -0.06
     왕
    -0.06
    administr
    -0.06
     gint
    -0.06
    ρούν
    -0.06
     sentencing
    -0.06
    POSITIVE LOGITS
    .ll
    0.06
     çıkar
    0.06
    (Encoding
    0.06
     Москов
    0.06
    уму
    0.06
    структор
    0.06
    .ci
    0.06
    uto
    0.06
    selling
    0.06
    ้าร
    0.06
    Act Density 0.007%

    No Known Activations