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

    Neuronpedia

    INDEX
    Explanations

    cout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sob
    -0.07
     hedge
    -0.07
     б
    -0.07
    ({"
    -0.07
    _Free
    -0.07
    _RE
    -0.07
     обо
    -0.07
    薄
    -0.06
     materiál
    -0.06
    -archive
    -0.06
    POSITIVE LOGITS
     casual
    0.07
    oubles
    0.07
    cott
    0.06
     Proud
    0.06
    (EIF
    0.06
     Compar
    0.06
     Cena
    0.06
     broadcast
    0.06
    (docs
    0.06
    Released
    0.06
    Act Density 0.003%

    No Known Activations