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

    Neuronpedia

    INDEX
    Explanations

    alternative medicine, less than a year, refund, experimental

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ف
    1.05
    4
    1.03
    5
    0.98
    9
    0.97
    0
    0.95
    2
    0.92
    6
    0.91
    3
    0.89
    ください
    0.89
    ור
    0.88
    POSITIVE LOGITS
    ેલા
    0.89
    不及
    0.79
    theless
    0.77
    釟
    0.75
    ...\...\
    0.74
    霄
    0.74
    عة
    0.73
    гы
    0.72
    。)
    0.72
    ないので
    0.71
    Act Density 0.000%

    No Known Activations