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

    Neuronpedia

    INDEX
    Explanations

    past states leading to outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     باید
    0.58
    ించాలి
    0.51
     puedo
    0.50
    会有
    0.50
     nếu
    0.49
    যদি
    0.49
     Jeśli
    0.48
     ঘটছে
    0.48
     এখনই
    0.48
     jeśli
    0.47
    POSITIVE LOGITS
     damals
    0.99
     damal
    0.98
     buvo
    0.96
     was
    0.95
     était
    0.90
     became
    0.87
     ήταν
    0.85
    became
    0.85
    当时
    0.84
    當時
    0.84
    Act Density 0.201%

    No Known Activations