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

    Neuronpedia

    INDEX
    Explanations

    reporting speech or statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beispielsweise
    0.42
    崎
    0.38
    ︵
    0.37
     DEALINGS
    0.37
    让人
    0.37
    లిన
    0.37
    allowSlide
    0.36
    欺
    0.36
    getResponse
    0.36
    λον
    0.35
    POSITIVE LOGITS
     likely
    0.50
    likely
    0.46
     Likely
    0.46
     if
    0.45
     wear
    0.43
     चरण
    0.43
    建議
    0.43
     write
    0.42
     suggested
    0.42
    すれば
    0.42
    Act Density 0.004%

    No Known Activations