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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    auga
    -0.07
    rang
    -0.07
    _dicts
    -0.07
    (vector
    -0.07
     Official
    -0.06
     Bren
    -0.06
    }],↵
    -0.06
    FR
    -0.06
    sob
    -0.06
     MDMA
    -0.06
    POSITIVE LOGITS
     Thường
    0.07
    _MODE
    0.06
    Sold
    0.06
     converged
    0.06
    stay
    0.06
    сом
    0.06
    wed
    0.06
     sağlam
    0.06
     Birleşik
    0.06
    ipi
    0.06
    Act Density 0.024%

    No Known Activations