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

    Neuronpedia

    INDEX
    Explanations

    The Simpsons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    יי
    0.84
    </b>
    0.72
     has
    0.68
     moons
    0.65
    ό
    0.64
     units
    0.63
    </strong>
    0.62
    ють
    0.62
     restricts
    0.62
    ม
    0.62
    POSITIVE LOGITS
    ्राफी
    0.62
     যায়
    0.61
     നൽക
    0.61
    partum
    0.57
    Detective
    0.57
    Dive
    0.57
    𝙩
    0.56
    edit
    0.55
    orest
    0.55
    tumor
    0.55
    Act Density 0.001%

    No Known Activations