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

    Neuronpedia

    INDEX
    Explanations

    instructions or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afirm
    0.42
     dif
    0.38
    Ба
    0.37
    ﺐ
    0.37
     sente
    0.37
     sostiene
    0.37
     việc
    0.36
     création
    0.36
     zaten
    0.36
    ễm
    0.36
    POSITIVE LOGITS
     Please
    0.45
    Try
    0.42
     Try
    0.41
    nPlease
    0.39
    shore
    0.39
    writerow
    0.38
     মার্কেটিং
    0.38
     pave
    0.38
    please
    0.38
     please
    0.37
    Act Density 0.000%

    No Known Activations