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

    Neuronpedia

    INDEX
    Explanations

    how they did it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⲃ
    0.52
     संघटना
    0.51
     westward
    0.50
    の良い
    0.50
     члены
    0.49
     सदस्य
    0.49
    |^{-
    0.49
    になった
    0.48
    рес
    0.48
    自治
    0.48
    POSITIVE LOGITS
    ä
    0.52
     מש
    0.51
     listopadu
    0.48
    table
    0.47
     maíz
    0.47
    ment
    0.47
     मा
    0.46
     både
    0.46
    for
    0.46
    äure
    0.45
    Act Density 0.000%

    No Known Activations