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

    Neuronpedia

    INDEX
    Explanations

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nauchno
    0.34
     monod
    0.30
    Province
    0.28
     змін
    0.28
    对照
    0.28
     Romano
    0.28
    当量
    0.28
    ⇔
    0.28
    墻
    0.28
    Moon
    0.27
    POSITIVE LOGITS
     uh
    0.54
     speaker
    0.52
    uh
    0.49
     Yeah
    0.47
    speaker
    0.46
    Speaker
    0.46
     yeah
    0.45
    okay
    0.44
    Okay
    0.42
     chuck
    0.42
    Act Density 0.002%

    No Known Activations