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

    Neuronpedia

    INDEX
    Explanations

    examination reveals outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     свидетель
    0.58
     implying
    0.57
     suggesting
    0.56
     مبنی
    0.50
     indicating
    0.49
     indiquant
    0.49
     संकेत
    0.47
    indicating
    0.47
     सांगतात
    0.46
     evidence
    0.46
    POSITIVE LOGITS
     yielded
    0.75
     yields
    0.73
     Yield
    0.69
    Yield
    0.67
     yield
    0.65
    yield
    0.62
     yielding
    0.57
     immediately
    0.46
     netted
    0.42
     Produce
    0.42
    Act Density 0.017%

    No Known Activations