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

    Neuronpedia

    INDEX
    Explanations

    Square roots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _reads
    -0.07
     Ragnar
    -0.07
    '''↵
    -0.07
    _recv
    -0.06
    						
↵
    -0.06
    /↵↵↵↵
    -0.06
     );
↵
↵
    -0.06
    河北省
    -0.06
    黎明
    -0.06
    .inverse
    -0.06
    POSITIVE LOGITS
    iphy
    0.07
    ooting
    0.07
    emento
    0.07
    낫
    0.06
     disparity
    0.06
    ㍑
    0.06
    瑬
    0.06
    邡
    0.06
     touching
    0.06
     facial
    0.06
    Act Density 0.007%

    No Known Activations