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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     начало
    0.41
    ați
    0.41
    рани
    0.40
    琹
    0.40
     možnosti
    0.40
     sucked
    0.40
     জারি
    0.39
     robbed
    0.38
    attractive
    0.38
    žno
    0.38
    POSITIVE LOGITS
     Caus
    0.67
    Cause
    0.64
     Cause
    0.60
    cause
    0.60
     cause
    0.58
     caus
    0.56
    OfDeath
    0.55
    ening
    0.54
    Causes
    0.54
     causar
    0.50
    Act Density 0.015%

    No Known Activations