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

    Neuronpedia

    INDEX
    Explanations

    common word sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     questions
    0.41
     word
    0.37
     первич
    0.37
     Questions
    0.37
    記事
    0.36
     whitespace
    0.36
     lying
    0.35
     soundtrack
    0.35
     토
    0.35
     capable
    0.34
    POSITIVE LOGITS
    劣化
    0.42
    planned
    0.41
    isolated
    0.39
    ᒫ
    0.39
    grace
    0.38
    ActionResult
    0.37
    oor
    0.37
     Nantucket
    0.37
    tunnel
    0.37
    holung
    0.37
    Act Density 0.000%

    No Known Activations