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

    Neuronpedia

    INDEX
    Explanations

    associated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fuji
    -0.07
    ȗ
    -0.07
    дра
    -0.07
    懵
    -0.07
     подготовк
    -0.07
    䴀
    -0.07
    embros
    -0.07
     RAND
    -0.07
     stern
    -0.06
    ERRU
    -0.06
    POSITIVE LOGITS
    亿元
    0.07
     *↵↵
    0.07
     outlet
    0.07
     ↵		↵
    0.07
    铝合金
    0.07
    套
    0.07
     aster
    0.07
     QLineEdit
    0.07
    >$
    0.07
    通
    0.07
    Act Density 0.001%

    No Known Activations