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

    Neuronpedia

    INDEX
    Explanations

    duct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    floating
    -0.07
    สรร
    -0.07
     prime
    -0.07
     الأساس
    -0.07
     ACE
    -0.07
    	long
    -0.07
    첨
    -0.06
    锾
    -0.06
    兄
    -0.06
    🕙
    -0.06
    POSITIVE LOGITS
    듄
    0.09
    人寿
    0.08
    Pad
    0.07
    通胀
    0.07
    umption
    0.07
    禒
    0.07
    _URL
    0.07
    /compiler
    0.07
    uckle
    0.06
    प
    0.06
    Act Density 0.004%

    No Known Activations