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

    Neuronpedia

    INDEX
    Explanations

    dressing modestly or dynamically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    noisy
    0.56
    கிர
    0.53
    installed
    0.51
    Су
    0.51
    פת
    0.51
    selected
    0.50
    educated
    0.50
    greedy
    0.50
    incoming
    0.50
    ждён
    0.50
    POSITIVE LOGITS
    ൂര
    0.44
     lien
    0.43
    وار
    0.43
     role
    0.43
     lint
    0.43
     workpiece
    0.42
     Wages
    0.42
     lattice
    0.41
     cli
    0.41
     länge
    0.41
    Act Density 0.000%

    No Known Activations