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

    Neuronpedia

    INDEX
    Explanations

    disaster

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    也是很
    -0.09
     двор
    -0.07
    Intro
    -0.07
     Twilight
    -0.07
     starred
    -0.07
    Aligned
    -0.07
    先是
    -0.07
     ncols
    -0.07
    欄
    -0.07
     AttributeError
    -0.07
    POSITIVE LOGITS
    דמות
    0.07
     đơn
    0.07
     remote
    0.07
     appliance
    0.06
    &quot
    0.06
    堰
    0.06
     diminishing
    0.06
    👙
    0.06
     når
    0.06
    ഫ
    0.06
    Act Density 0.006%

    No Known Activations