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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "L
    -0.07
    Пр
    -0.07
     smoke
    -0.06
     asia
    -0.06
     thường
    -0.06
    'order
    -0.06
     Ди
    -0.06
     onResume
    -0.06
    „P
    -0.06
     tob
    -0.06
    POSITIVE LOGITS
    علام
    0.07
    =options
    0.06
    =self
    0.06
    >xpath
    0.06
    .Notification
    0.06
    �
    0.06
    α
    0.06
    ارات
    0.06
    ист
    0.06
     verbess
    0.06
    Act Density 0.077%

    No Known Activations