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

    Neuronpedia

    INDEX
    Explanations

    Dates and date mentions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'A
    -0.08
    WASHINGTON
    -0.07
     LA
    -0.07
    -t
    -0.06
    'S
    -0.06
     MODEL
    -0.06
    (dev
    -0.06
    YST
    -0.06
     marched
    -0.06
    _t
    -0.06
    POSITIVE LOGITS
     Yardım
    0.07
    ｱ
    0.07
    .offsetWidth
    0.06
     başarılı
    0.06
    osyal
    0.06
     vivastreet
    0.06
    ddit
    0.06
    .dismiss
    0.06
    .fillStyle
    0.06
     expres
    0.06
    Act Density 0.008%

    No Known Activations