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

    Neuronpedia

    INDEX
    Explanations

    professional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MR
    -0.07
    apatkan
    -0.07
    油
    -0.06
    氧
    -0.06
    ở
    -0.06
    ncia
    -0.06
     bindings
    -0.06
    선거
    -0.06
     нашей
    -0.06
    ़
    -0.06
    POSITIVE LOGITS
     वजह
    0.07
    (i
    0.07
    (img
    0.06
     lifted
    0.06
    囲
    0.06
     Schiff
    0.06
    �合
    0.06
    Preferred
    0.06
    	index
    0.06
    (substr
    0.06
    Act Density 0.017%

    No Known Activations