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

    Neuronpedia

    INDEX
    Explanations

    chemical compound instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    रिया
    0.40
    シャン
    0.39
    烣
    0.39
     enak
    0.37
    跹
    0.37
     عنده
    0.37
     onFailure
    0.37
     verloren
    0.36
     veren
    0.36
    amek
    0.36
    POSITIVE LOGITS
     H
    0.49
    内置
    0.43
     intercept
    0.43
     lettuce
    0.42
     হ
    0.41
     타입
    0.39
     cashmere
    0.38
     Lettuce
    0.37
    Ham
    0.36
     lib
    0.36
    Act Density 0.000%

    No Known Activations