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

    Neuronpedia

    INDEX
    Explanations

    wisdom and wise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হানাদার
    0.90
    بعا
    0.85
    ation
    0.85
    レーション
    0.84
    iation
    0.82
    대전
    0.81
    ATION
    0.81
    adium
    0.81
    inations
    0.80
    吁
    0.80
    POSITIVE LOGITS
     Wisdom
    1.34
     Wise
    1.26
     wisdom
    1.26
     Proverbs
    1.24
    Wis
    1.14
     wise
    1.12
     sabiduría
    1.07
    Wise
    1.05
    wisdom
    1.01
     wisely
    0.97
    Act Density 0.040%

    No Known Activations