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

    Neuronpedia

    INDEX
    Explanations

    difference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Card
    -0.06
     chez
    -0.06
     Acres
    -0.06
    -Americans
    -0.06
     Rotary
    -0.06
     amb
    -0.06
     Як
    -0.06
     BEST
    -0.06
     �
    -0.06
    德
    -0.06
    POSITIVE LOGITS
    avirus
    0.07
    undance
    0.06
     ژاپ
    0.06
    ุน
    0.06
    	ar
    0.06
    UGH
    0.06
    .'"↵↵
    0.06
    ','$
    0.06
     emotionally
    0.06
    flatMap
    0.06
    Act Density 0.041%

    No Known Activations