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

    Neuronpedia

    INDEX
    Explanations

    can be used or adapted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berücksichtigt
    0.44
     revisions
    0.43
    確保
    0.42
    using
    0.40
    σκε
    0.40
    ennem
    0.39
     umož
    0.39
    options
    0.38
     adjustments
    0.38
     ensure
    0.38
    POSITIVE LOGITS
     enjoyed
    0.50
    媲
    0.43
     পণ
    0.42
     operated
    0.41
     pair
    0.40
     mould
    0.40
    Excellent
    0.39
     দারুণ
    0.39
     മികച്ച
    0.39
     odlič
    0.39
    Act Density 0.016%

    No Known Activations