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

    Neuronpedia

    INDEX
    Explanations

    un- words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.72
    d
    0.63
    า
    0.59
     पूछते
    0.57
    ו
    0.56
    dalam
    0.55
    و
    0.55
    ↵↵
    0.52
    g
    0.50
    ᱶ
    0.50
    POSITIVE LOGITS
     un
    0.99
     Un
    0.69
     risked
    0.64
     unha
    0.62
     unveiled
    0.61
     अन
    0.59
     una
    0.56
    Un
    0.56
    ین
    0.55
     unatt
    0.55
    Act Density 0.019%

    No Known Activations