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

    Neuronpedia

    INDEX
    Explanations

    Blockers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     နောက်
    0.51
     არს
    0.48
    នៅក្នុង
    0.48
    mas
    0.46
     アー
    0.45
     masch
    0.45
    ネイ
    0.45
    限界
    0.45
     インド
    0.45
    詳しくは
    0.45
    POSITIVE LOGITS
    istar
    0.52
     kanya
    0.46
    cinn
    0.44
    lád
    0.43
    ummy
    0.42
     fark
    0.40
     doble
    0.40
     tourn
    0.39
    жный
    0.39
    办法
    0.39
    Act Density 0.001%

    No Known Activations