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

    Neuronpedia

    INDEX
    Explanations

    finding oneself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лиги
    0.35
     Кто
    0.35
    Container
    0.34
     Конечно
    0.34
    ник
    0.34
    ель
    0.34
    Skill
    0.33
    Utilization
    0.33
    ielle
    0.32
    ld
    0.32
    POSITIVE LOGITS
     it
    0.56
     himself
    0.45
     sobie
    0.45
     themselves
    0.44
     offensive
    0.44
     most
    0.43
     offense
    0.43
     себя
    0.42
     solace
    0.42
     that
    0.40
    Act Density 0.009%

    No Known Activations