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

    Neuronpedia

    INDEX
    Explanations

    learning and myths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ту
    0.52
    ↵
    0.50
    ل
    0.50
    ü
    0.47
    fit
    0.46
     Flooring
    0.46
    ки
    0.46
     Meeting
    0.44
    st
    0.42
     SSC
    0.42
    POSITIVE LOGITS
     პარ
    0.49
     Đá
    0.48
     канторы
    0.46
     वाटते
    0.46
     její
    0.44
    Χ
    0.43
     دیے
    0.43
    সকল
    0.42
     εύ
    0.42
    铳
    0.42
    Act Density 0.009%

    No Known Activations