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

    Neuronpedia

    INDEX
    Explanations

    legalistic statements and disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    汔
    0.34
     শীঘ্রই
    0.30
    écution
    0.30
    汢
    0.30
    徝
    0.29
     Semua
    0.29
    を使う
    0.29
     Yama
    0.28
    !।
    0.28
    🔃
    0.28
    POSITIVE LOGITS
    ,
    0.28
      
    0.27
    -
    0.27
     ,
    0.26
    p
    0.25
    ↵
    0.25
    ↵↵
    0.24
    <0xC2>
    0.24
     precursor
    0.22
     valued
    0.22
    Act Density 0.005%

    No Known Activations