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

    Neuronpedia

    INDEX
    Explanations

    Flashcards and quizzes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     controvers
    -0.09
    	strcat
    -0.09
    joining
    -0.08
    万人
    -0.08
     hieman
    -0.08
     strcat
    -0.08
     män
    -0.08
    哲
    -0.08
     handbook
    -0.08
     mennesker
    -0.08
    POSITIVE LOGITS
     जवाब
    0.09
     verbal
    0.08
     रोल
    0.08
     solicit
    0.08
     quizzes
    0.08
     idé
    0.08
     reverse
    0.07
    .flip
    0.07
     modalities
    0.07
     flip
    0.07
    Act Density 0.012%

    No Known Activations