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

    Neuronpedia

    INDEX
    Explanations

    media and news sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    我们需要
    0.31
    l
    0.30
    众多
    0.27
    <unused292>
    0.27
    ロット
    0.27
    参数
    0.26
    ᴍ
    0.26
    R
    0.25
    <unused260>
    0.25
     Hein
    0.25
    POSITIVE LOGITS
     ducha
    0.36
     website
    0.33
     muzy
    0.32
    ²,
    0.31
     tarz
    0.31
     https
    0.31
     deportation
    0.30
     tiež
    0.30
     loves
    0.30
     mujer
    0.29
    Act Density 0.132%

    No Known Activations