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

    Neuronpedia

    INDEX
    Explanations

    `el` variable or identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     イラストレーション
    -2.75
     $_(
    -2.52
    絰
    -2.45
     バッグ
    -2.34
     現貨
    -2.33
    踽
    -2.33
    趿
    -2.31
     花纹
    -2.30
     菇
    -2.30
    ၟ
    -2.28
    POSITIVE LOGITS
     
    2.50
     "
    2.39
    ⇹
    2.31
     его
    2.09
     l
    2.06
    眼光
    2.05
    マニア
    1.95
     ‘
    1.89
     `
    1.89
    ℟
    1.88
    Act Density 0.002%

    No Known Activations