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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اوت
    -0.07
     заг
    -0.06
    스티
    -0.06
    _minutes
    -0.06
     blatant
    -0.06
    τά
    -0.06
    commended
    -0.06
    acial
    -0.06
     patents
    -0.06
     ارزی
    -0.06
    POSITIVE LOGITS
    ...]↵↵
    0.07
     politics
    0.07
    �
    0.07
    대학
    0.06
    Kitchen
    0.06
    .SIZE
    0.06
     Portfolio
    0.06
    vrolet
    0.06
     duy
    0.06
     الأول
    0.06
    Act Density 0.006%

    No Known Activations