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

    Neuronpedia

    INDEX
    Explanations

    proposed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chained
    -0.06
     EMP
    -0.06
     Müş
    -0.06
     Uganda
    -0.06
     み
    -0.06
    draul
    -0.06
     Skill
    -0.06
    .books
    -0.06
     Fever
    -0.06
    ker
    -0.06
    POSITIVE LOGITS
    ribly
    0.07
    　ヾ
    0.06
    iệt
    0.06
    Utils
    0.06
    mark
    0.06
    __()
    0.06
    oya
    0.06
     discreet
    0.06
     AssetImage
    0.06
     ><?
    0.06
    Act Density 0.006%

    No Known Activations