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

    Neuronpedia

    INDEX
    Explanations

    GUI code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🃏
    -0.07
    獍
    -0.07
    izzes
    -0.07
    isspace
    -0.07
     SEA
    -0.06
    שוקולד
    -0.06
    SCRI
    -0.06
    有序推进
    -0.06
    .clientX
    -0.06
     would
    -0.06
    POSITIVE LOGITS
    中间
    0.07
    柔和
    0.07
     neben
    0.07
     Favorite
    0.06
    褥
    0.06
    模型
    0.06
     Registry
    0.06
    힌
    0.06
    镜子
    0.06
    蓝
    0.06
    Act Density 0.010%

    No Known Activations