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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    athy
    -0.07
    лы
    -0.07
    @Named
    -0.07
    �
    -0.07
     unsuccessful
    -0.07
     musicals
    -0.07
     machining
    -0.07
     local
    -0.07
    -0.07
     disliked
    -0.07
    POSITIVE LOGITS
     bon
    0.09
     判断
    0.09
     判
    0.09
    Iterator
    0.09
     Iterator
    0.08
     校
    0.08
     iterator
    0.08
     കൂട്ട
    0.08
     Advantages
    0.08
    	Iterator
    0.08
    Act Density 0.006%
    No Known Activations