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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     players
    0.50
    D
    0.49
    astern
    0.47
     D
    0.46
    </td>
    0.45
    en
    0.45
     (
    0.45
     balanced
    0.45
     can
    0.45
    {
    0.44
    POSITIVE LOGITS
     splike
    0.56
     只
    0.49
    𒋼
    0.48
     अराउंड
    0.48
     resultó
    0.47
    രാഷ്ട്ര
    0.47
    ▃
    0.47
     sporad
    0.46
    𒊏
    0.46
     biện
    0.46
    Act Density 0.003%

    No Known Activations