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

    Neuronpedia

    INDEX
    Explanations

    Tricky parts or findings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIF
    -0.07
    Leon
    -0.06
     nutritious
    -0.06
    _for
    -0.06
     lh
    -0.06
     Buchanan
    -0.06
    -pos
    -0.06
    Fans
    -0.06
    zimmer
    -0.06
    allon
    -0.06
    POSITIVE LOGITS
     nobody
    0.07
     ourselves
    0.06
     elect
    0.06
     région
    0.06
     مشکلات
    0.06
    "title
    0.06
     developments
    0.06
     myself
    0.06
    自身
    0.06
     зробити
    0.06
    Act Density 0.141%

    No Known Activations