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

    Neuronpedia

    INDEX
    Explanations

    Glass, pairwise correlation, disjoint sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wok
    0.52
     attentively
    0.49
    దే
    0.48
     líqu
    0.48
    स्टेबल
    0.46
    îte
    0.46
     coales
    0.46
    setMin
    0.46
     disappoint
    0.45
    ęż
    0.45
    POSITIVE LOGITS
    Voir
    0.53
    IA
    0.52
    IAMS
    0.47
    Y
    0.47
    Club
    0.47
    Cancer
    0.46
     حملہ
    0.46
    Batman
    0.46
     现在
    0.46
    ი
    0.45
    Act Density 0.000%

    No Known Activations