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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    樽
    -0.07
     Charles
    -0.07
    звук
    -0.07
     phantom
    -0.07
     предн
    -0.07
     operators
    -0.07
     период
    -0.07
    phase
    -0.07
    �
    -0.07
    潭
    -0.07
    POSITIVE LOGITS
    ḃ
    0.08
     brib
    0.07
    生活习惯
    0.07
    畜牧业
    0.07
    ruits
    0.07
     הלב
    0.06
    }`);↵
    0.06
    ߤ
    0.06
    PTION
    0.06
    迪拜
    0.06
    Act Density 0.041%

    No Known Activations