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

    Neuronpedia

    INDEX
    Explanations

    beanie, inflammation, pros, stronger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    მას
    0.54
    when
    0.54
    马
    0.50
     Passo
    0.50
    anym
    0.49
    นะ
    0.47
    म
    0.47
    mują
    0.44
    у
    0.44
    during
    0.43
    POSITIVE LOGITS
     travailleurs
    0.49
     meats
    0.46
     humides
    0.46
     planks
    0.46
     wedges
    0.45
     labors
    0.44
     والمع
    0.43
     δυ
    0.43
     gaskets
    0.43
     slopes
    0.43
    Act Density 0.001%

    No Known Activations