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

    Neuronpedia

    INDEX
    Explanations

    emojis and their combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ️
    0.93
    ︎
    0.88
    ‍
    0.65
    ‍♀️
    0.64
     ‍
    0.55
    ‍♂
    0.54
    ˒
    0.52
    ‍♀
    0.52
    ‍♂️
    0.49
     ♡
    0.47
    POSITIVE LOGITS
    🙏🙏
    0.61
    👏👏👏👏
    0.56
    👏👏
    0.51
    🙏🏻
    0.47
    😭😭
    0.44
    👍
    0.43
    😑
    0.41
    🤷
    0.40
    😧
    0.40
    🖒
    0.40
    Act Density 0.001%

    No Known Activations