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

    Neuronpedia

    INDEX
    Explanations

    how to explain or solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     practices
    0.41
     onderwerp
    0.41
     নির্দিষ্ট
    0.39
    ঁপ
    0.38
    iejsc
    0.38
     cristall
    0.37
    র্তি
    0.37
     всем
    0.37
    prechen
    0.37
     intensely
    0.36
    POSITIVE LOGITS
    OWA
    0.40
     όσο
    0.38
    们的
    0.38
     값이
    0.38
     Bit
    0.37
     \$
    0.37
    গুলির
    0.37
    GPA
    0.37
    随着
    0.37
    どんどん
    0.37
    Act Density 0.000%

    No Known Activations