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

    Neuronpedia

    INDEX
    Explanations

    "my go-to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flies
    -0.07
     options
    -0.07
     。
    -0.07
    .Widget
    -0.07
     viewing
    -0.06
     ）↵
    -0.06
    ее
    -0.06
    qtt
    -0.06
    Archive
    -0.06
    лив
    -0.06
    POSITIVE LOGITS
     　　 　
    0.07
     близ
    0.06
    سنگ
    0.06
     Seam
    0.06
    ВА
    0.06
    eldo
    0.06
    affen
    0.06
     ответствен
    0.06
     Advis
    0.06
     Peb
    0.06
    Act Density 0.070%

    No Known Activations