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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    аду
    -0.07
    ‌ال
    -0.07
    _news
    -0.06
    rack
    -0.06
    casts
    -0.06
    chts
    -0.06
    bower
    -0.06
    (The
    -0.06
    Cause
    -0.06
     Dennis
    -0.06
    POSITIVE LOGITS
     세계
    0.07
    observe
    0.07
     cardiovascular
    0.06
    ปฏ
    0.06
    -del
    0.06
    ;}
↵
    0.06
    *******************************************************************************/↵
    0.06
     indexing
    0.06
    盗
    0.06
    	card
    0.06
    Act Density 0.012%

    No Known Activations