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

    Neuronpedia

    INDEX
    Explanations

    anything else or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nếu
    0.59
     jika
    0.55
     если
    0.53
     jeśli
    0.53
     যদি
    0.49
    IfNeeded
    0.49
     Если
    0.47
     eğer
    0.47
     यदि
    0.47
     wenn
    0.46
    POSITIVE LOGITS
    note
    0.43
    besides
    0.40
     perils
    0.40
    gems
    0.40
     besides
    0.38
     amid
    0.38
     reflections
    0.37
     ubiquitous
    0.37
     proverbial
    0.37
    warnings
    0.37
    Act Density 0.001%

    No Known Activations