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

    Neuronpedia

    INDEX
    Explanations

    .com URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⅵ
    0.36
     robustness
    0.32
    狨
    0.32
    DataDiv
    0.32
     devaluation
    0.32
     النسبيه
    0.31
     श्रमिकों
    0.30
    📉
    0.30
    Ⅷ
    0.30
    必须
    0.29
    POSITIVE LOGITS
    <start_of_image>
    0.39
    h
    0.32
     pr
    0.32
    f
    0.31
    hés
    0.30
    cB
    0.30
    ob
    0.30
    They
    0.29
    Notably
    0.29
    So
    0.29
    Act Density 0.009%

    No Known Activations