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

    Neuronpedia

    INDEX
    Explanations

    Python code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ==(
    0.97
    だったので
    0.96
     THERE
    0.95
     `=`,
    0.95
     뭘
    0.95
     there
    0.94
    やはり
    0.92
    ++);
    0.91
     último
    0.89
     secondly
    0.89
    POSITIVE LOGITS
    "
    0.83
    """
    0.80
    "]
    0.71
    *"
    0.70
    ."
    0.69
    "*
    0.67
     Assists
    0.66
     يح
    0.66
    ↵
    0.66
    \
    0.65
    Act Density 0.138%

    No Known Activations