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

    Neuronpedia

    INDEX
    Explanations

    said, Here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    макраты
    0.38
    новним
    0.38
     basilaires
    0.38
    ління
    0.37
    новни
    0.37
    द्वीप
    0.36
    ladesh
    0.36
    isy
    0.36
    nants
    0.36
    ជាតិ
    0.35
    POSITIVE LOGITS
    Anyways
    0.50
     Anyways
    0.48
     Alors
    0.45
     Anyway
    0.43
     পর্যবেক্ষণ
    0.43
     Alright
    0.41
     Beur
    0.40
     த
    0.40
     Thus
    0.39
    那麼
    0.39
    Act Density 0.077%

    No Known Activations