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

    Neuronpedia

    INDEX
    Explanations

    collections of papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $text
    -0.07
    █
    -0.06
     PlayStation
    -0.06
     klik
    -0.06
     badass
    -0.06
    *"
    -0.06
     정확
    -0.06
     ambassador
    -0.06
     симптом
    -0.06
    Compact
    -0.06
    POSITIVE LOGITS
    CHED
    0.07
     Deleted
    0.07
    ıydı
    0.07
    迪
    0.06
     który
    0.06
    оре
    0.06
    หน
    0.06
     hubs
    0.06
    COORD
    0.06
    odel
    0.06
    Act Density 0.018%

    No Known Activations