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

    Neuronpedia

    INDEX
    Explanations

    translates to or sums to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emphasis
    0.84
     persistent
    0.79
     persisting
    0.77
     rivet
    0.77
     emphasized
    0.76
     emphasize
    0.75
     ability
    0.75
    มากขึ้น
    0.75
     speculated
    0.74
     Persistent
    0.74
    POSITIVE LOGITS
    тва
    0.76
    ranno
    0.72
    ោក
    0.72
    cesz
    0.72
     dizer
    0.72
     roughly
    0.72
    Ꭱ
    0.70
    to
    0.70
    Lah
    0.70
    mam
    0.70
    Act Density 0.021%

    No Known Activations