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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ))),
    -0.07
     For
    -0.07
    getMockBuilder
    -0.06
     Ти
    -0.06
     Holy
    -0.06
    OVER
    -0.06
    Vert
    -0.06
    优秀
    -0.06
    CreateTime
    -0.06
    	ID
    -0.06
    POSITIVE LOGITS
     phụ
    0.07
    $x
    0.07
     crab
    0.07
     Blick
    0.07
    -an
    0.06
     avec
    0.06
     Daniels
    0.06
    —an
    0.06
     dash
    0.06
     teenage
    0.06
    Act Density 0.065%

    No Known Activations