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

    Neuronpedia

    INDEX
    Explanations

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h4>
    0.69
    <h2>
    0.68
     ordained
    0.66
    אם
    0.66
     protéines
    0.64
    StillWater
    0.63
     któ
    0.61
    ルの
    0.61
     plastique
    0.61
    ᾧ
    0.60
    POSITIVE LOGITS
    te
    1.02
    k
    0.96
    ul
    0.89
    ale
    0.86
    eg
    0.85
    ა
    0.85
    et
    0.84
    ant
    0.84
    ha
    0.83
    re
    0.82
    Act Density 0.233%

    No Known Activations