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

    Neuronpedia

    INDEX
    Explanations

    color and text formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اکہ
    0.47
    Baş
    0.45
    ना
    0.43
    ف
    0.43
    THAT
    0.43
    ම්භ
    0.43
    ා
    0.42
    قب
    0.41
     انٹر
    0.41
    positroid
    0.41
    POSITIVE LOGITS
     type
    0.51
     people
    0.49
     showroom
    0.47
     людьми
    0.47
     downturn
    0.46
     introduced
    0.46
     dark
    0.45
     body
    0.45
     customer
    0.45
     navy
    0.43
    Act Density 0.000%

    No Known Activations