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

    Neuronpedia

    INDEX
    Explanations

    c++ output stream manipulators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ])*
    0.43
    Adorable
    0.41
    眼
    0.41
    legate
    0.41
    бие
    0.41
    斤
    0.40
    лых
    0.40
    vej
    0.40
    াপ্র
    0.40
    ayeva
    0.39
    POSITIVE LOGITS
     endl
    0.98
    endl
    0.96
     flush
    0.71
     <<
    0.69
     Flush
    0.68
     setw
    0.66
     manipulator
    0.66
    flush
    0.65
     flushing
    0.65
    Flush
    0.65
    Act Density 0.019%

    No Known Activations