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

    Neuronpedia

    INDEX
    Explanations

    default

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chaos
    -0.06
     hacia
    -0.06
    acción
    -0.06
     závod
    -0.06
    鮮
    -0.06
    -0.06
     Swansea
    -0.06
    .imread
    -0.06
     طلا
    -0.06
     важно
    -0.06
    POSITIVE LOGITS
    wx
    0.07
    γον
    0.07
    sylvania
    0.07
     truck
    0.06
     dB
    0.06
    many
    0.06
     thoroughly
    0.06
     обеспе
    0.06
     obtain
    0.06
    "]
↵
    0.06
    Act Density 0.009%

    No Known Activations