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

    Neuronpedia

    INDEX
    Explanations

    Raises exceptions or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     želite
    0.39
    ᄆ
    0.39
    蔔
    0.36
    సా
    0.35
     давайте
    0.34
    宠物
    0.34
    忘れ
    0.34
    楶
    0.34
    ফট
    0.34
    수로
    0.33
    POSITIVE LOGITS
     Also
    0.57
     also
    0.52
    Also
    0.47
    also
    0.46
     также
    0.46
     також
    0.46
     Examples
    0.44
    throws
    0.44
     incluye
    0.44
     includes
    0.43
    Act Density 0.018%

    No Known Activations