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

    Neuronpedia

    INDEX
    Explanations

    between values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hacks
    0.46
     Ridley
    0.44
     Nakamura
    0.43
     hacks
    0.43
     zombies
    0.42
     Couture
    0.42
     vocabulary
    0.42
     Kata
    0.41
     Nade
    0.41
     subjectivity
    0.41
    POSITIVE LOGITS
    preferably
    0.46
    ้า
    0.43
    できる
    0.43
    冲突
    0.43
    スキー
    0.43
    ding
    0.42
    可以
    0.42
    顺利
    0.42
    三
    0.42
    ുമു
    0.41
    Act Density 0.000%

    No Known Activations