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

    Neuronpedia

    INDEX
    Explanations

    examine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уска
    -0.09
     �
    -0.08
    غا
    -0.08
     Alma
    -0.07
    /F
    -0.07
     nous
    -0.07
    /Linux
    -0.07
    -certified
    -0.07
     回
    -0.07
     deste
    -0.07
    POSITIVE LOGITS
    一下
    0.11
     thoroughly
    0.08
     circumstances
    0.08
     вариантов
    0.07
    টির
    0.07
     возможность
    0.07
    Temporal
    0.07
    558
    0.07
     деталей
    0.07
     দেখ
    0.07
    Act Density 0.024%

    No Known Activations