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

    Neuronpedia

    INDEX
    Explanations

    scan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <H
    -0.08
     וז
    -0.08
    不是
    -0.08
    😙
    -0.07
    appings
    -0.07
    ОР
    -0.07
    对公司
    -0.07
    有多大
    -0.07
    اعدة
    -0.07
     Killing
    -0.07
    POSITIVE LOGITS
     Güncelle
    0.07
     scans
    0.07
     punishable
    0.07
     threat
    0.07
     millennium
    0.07
    \",\
    0.07
     psyched
    0.07
    겚
    0.07
     scan
    0.07
    frm
    0.07
    Act Density 0.013%

    No Known Activations