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

    Neuronpedia

    INDEX
    Explanations

    Instructions and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inserting
    -0.09
     holidays
    -0.08
    prowad
    -0.08
     oldukça
    -0.08
    ił
    -0.08
    謝
    -0.08
    <Comment
    -0.08
    ollapse
    -0.08
    ίκ
    -0.07
    <Member
    -0.07
    POSITIVE LOGITS
     checking
    0.09
    检查
    0.09
    チェック
    0.09
     vetted
    0.09
     letten
    0.09
     vérifier
    0.08
     candidate
    0.08
    衡
    0.08
    checking
    0.08
     trustworthy
    0.08
    Act Density 0.137%

    No Known Activations