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

    Neuronpedia

    INDEX
    Explanations

    player behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    해
    0.52
    主義
    0.47
    設定
    0.46
    ิ
    0.45
    יו
    0.45
    يا
    0.43
    擾
    0.43
    圧倒
    0.42
    しい
    0.42
    וס
    0.42
    POSITIVE LOGITS
     objected
    0.54
     médiocrement
    0.52
     exhibited
    0.49
     championed
    0.48
     Recommended
    0.47
     disagreed
    0.46
     experimented
    0.46
     regretted
    0.45
     Dh
    0.45
     pivoted
    0.45
    Act Density 0.002%

    No Known Activations