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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     相
    -0.06
    죠
    -0.06
     reh
    -0.06
     adjoining
    -0.06
    �
    -0.06
     bass
    -0.06
    proto
    -0.06
    י�
    -0.06
     �
    -0.06
     Spear
    -0.06
    POSITIVE LOGITS
    ......
    0.07
    Explorer
    0.07
    ↵	↵
    0.07
    -interface
    0.06
            ↵    ↵
    0.06
     Prim
    0.06
     clashes
    0.06
                    ↵↵
    0.06
    웨디시
    0.06
    compression
    0.06
    Act Density 0.111%

    No Known Activations