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

    Neuronpedia

    INDEX
    Explanations

    java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瑨
    -0.07
    شمل
    -0.07
     redesigned
    -0.07
    핍
    -0.07
    �
    -0.06
    눇
    -0.06
    ԃ
    -0.06
     нагрузк
    -0.06
     deliberately
    -0.06
     diseñ
    -0.06
    POSITIVE LOGITS
    .then
    0.07
     (@
    0.07
    Vo
    0.07
    ('='
    0.07
    更加
    0.06
    ];↵
    0.06
    היסטוריה
    0.06
     Ngày
    0.06
    -series
    0.06
    lings
    0.06
    Act Density 0.009%

    No Known Activations