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

    Neuronpedia

    INDEX
    Explanations

    hypothetical/fictional scenarios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sr
    -0.09
     जाएगा
    -0.08
    Scratch
    -0.07
    ेमाल
    -0.07
    Lighting
    -0.07
    _CLASS
    -0.07
     ეხ
    -0.07
    Mailer
    -0.07
    Rp
    -0.07
    Class
    -0.07
    POSITIVE LOGITS
    0.08
     sej
    0.08
    دی
    0.07
     ture
    0.07
    STRUCTION
    0.07
     dinosaur
    0.07
     차량
    0.07
     공동
    0.07
     Find
    0.07
     penny
    0.07
    Act Density 0.000%
    No Known Activations