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

    Neuronpedia

    INDEX
    Explanations

    section numbers and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Whoever
    0.49
    Similarly
    0.47
    Alternatively
    0.47
    Remember
    0.47
    Additionally
    0.46
    اگر
    0.45
    Также
    0.44
    Если
    0.44
    Also
    0.43
    Many
    0.43
    POSITIVE LOGITS
    参考文献
    0.53
     subsection
    0.45
     subsections
    0.44
     discusses
    0.43
     subchapter
    0.41
    第三
    0.41
     chapter
    0.40
     III
    0.39
     discuss
    0.38
     포함
    0.38
    Act Density 0.002%

    No Known Activations