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

    Neuronpedia

    INDEX
    Explanations

    product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рам
    -0.08
    -sharing
    -0.07
    _unit
    -0.06
    ino
    -0.06
     Governors
    -0.06
     software
    -0.06
    .x
    -0.06
    encoder
    -0.06
    ूर
    -0.06
     NC
    -0.06
    POSITIVE LOGITS
     Vladimir
    0.07
    „N
    0.07
     neo
    0.06
     typo
    0.06
    اسات
    0.06
    „M
    0.06
    iological
    0.06
     objections
    0.06
     RVA
    0.06
     disparate
    0.06
    Act Density 0.061%

    No Known Activations