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

    Neuronpedia

    INDEX
    Explanations

    goal accomplishment and purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.61
     AND
    0.51
     coincident
    0.50
    ک
    0.50
     से
    0.49
     actuar
    0.49
     unrelated
    0.48
    ＞
    0.47
    Од
    0.47
     ח
    0.47
    POSITIVE LOGITS
    вел
    0.51
    ører
    0.50
     ازيكم
    0.49
     മുൻ
    0.47
    рд
    0.47
    enses
    0.46
     UnitTest
    0.46
    <0xB5>
    0.46
     COc
    0.46
     deklar
    0.46
    Act Density 0.000%

    No Known Activations