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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    paces
    -0.07
    𝕊
    -0.07
     irq
    -0.07
     fingertips
    -0.07
    nces
    -0.07
    الأر
    -0.07
    aviors
    -0.06
    עץ
    -0.06
     ribs
    -0.06
     ner
    -0.06
    POSITIVE LOGITS
    	addr
    0.07
    ال
    0.07
     Look
    0.06
     attached
    0.06
     Exact
    0.06
    interest
    0.06
    �
    0.06
    bookmark
    0.06
    =pd
    0.06
    时常
    0.06
    Act Density 0.083%

    No Known Activations