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

    Neuronpedia

    INDEX
    Explanations

    many, simple, near, security, regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    스
    0.40
     stellen
    0.40
     স্থিত
    0.40
    ρώ
    0.39
     కొత్త
    0.39
     knots
    0.39
     ordre
    0.38
     rask
    0.38
    त्तर
    0.38
     melaksanakan
    0.38
    POSITIVE LOGITS
     そして
    0.51
    لک
    0.49
     自動
    0.49
    injlim
    0.49
     کسی
    0.47
    groupBy
    0.47
     純正
    0.47
    アカウント
    0.46
     国内
    0.46
    ならでは
    0.46
    Act Density 0.006%

    No Known Activations