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

    Neuronpedia

    INDEX
    Explanations

    print statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পানি
    0.45
     الماء
    0.43
    পানি
    0.40
     পানির
    0.40
    の水
    0.40
     पाण्या
    0.39
     water
    0.39
     पानी
    0.39
     जल
    0.39
    ؛
    0.39
    POSITIVE LOGITS
    ("-"
    0.57
    ("\
    0.51
    ("")
    0.49
    ('
    0.49
    ("
    0.47
    ("{}
    0.47
    ("*
    0.46
    (
    0.46
    print
    0.46
    ('\
    0.45
    Act Density 0.006%

    No Known Activations