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

    Neuronpedia

    INDEX
    Explanations

    -Saharan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Retrofit
    -0.08
    net
    -0.07
     Scottish
    -0.07
    .sk
    -0.07
     tại
    -0.07
     ek
    -0.07
    Hôtel
    -0.07
    ekt
    -0.07
    到底
    -0.07
     DAM
    -0.07
    POSITIVE LOGITS
     تصني
    0.08
    حر
    0.08
    ᅮ
    0.07
    ]){
↵
    0.07
    纪委监
    0.07
    婚
    0.07
    xl
    0.06
    𬘫
    0.06
    ◈
    0.06
     unauthorized
    0.06
    Act Density 0.001%

    No Known Activations