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

    Neuronpedia

    INDEX
    Explanations

    state change or process applied

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imprescindible
    0.35
    കേന്ദ്രം
    0.34
     постепен
    0.33
    ของการ
    0.33
    стых
    0.33
     الوط
    0.32
    owość
    0.32
     ასევე
    0.31
     टॉपर
    0.31
     privind
    0.31
    POSITIVE LOGITS
     into
    0.44
    into
    0.38
     away
    0.35
    起来
    0.33
    ethylene
    0.33
     extensively
    0.32
     electrically
    0.32
     using
    0.31
     siguiendo
    0.31
     intravenously
    0.31
    Act Density 0.142%

    No Known Activations