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

    Neuronpedia

    INDEX
    Explanations

    discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.09
     is
    0.82
    ন
    0.82
    "
    0.79
     aérea
    0.79
    知道
    0.77
     извест
    0.76
    ിയ
    0.75
     experiment
    0.74
    machen
    0.74
    POSITIVE LOGITS
    discrimination
    1.05
     discrimination
    0.95
    ле
    0.92
    discrimin
    0.89
    ו
    0.86
     Discrimination
    0.84
    0
    0.78
    कारात्मक
    0.77
    x
    0.77
     ")
    0.73
    Act Density 0.007%

    No Known Activations