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

    Neuronpedia

    INDEX
    Explanations

    introduction or enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵↵
    0.49
    .”
    0.49
    ).\\
    0.48
    所以
    0.47
    ↵↵
    0.46
     প্রমুখ
    0.46
    .</
    0.45
    ).”
    0.44
    ៕
    0.44
     Etc
    0.43
    POSITIVE LOGITS
    。「
    0.67
     Öncelikle
    0.62
     Firstly
    0.59
    。“
    0.51
     প্রথমেই
    0.51
     firstly
    0.50
    。《
    0.50
     şöyle
    0.48
     있는데요
    0.48
     bijvoorbeeld
    0.48
    Act Density 0.032%

    No Known Activations