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

    Neuronpedia

    INDEX
    Explanations

    seul / only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     productos
    0.40
    शिव
    0.40
     familias
    0.39
    篷
    0.39
     produtos
    0.39
     chestnuts
    0.39
     politici
    0.38
     nostrum
    0.38
     campaigners
    0.38
     hilfreich
    0.38
    POSITIVE LOGITS
    alone
    0.55
     alone
    0.53
     மட்டுமே
    0.52
     أمام
    0.50
     seul
    0.43
    Alone
    0.42
     💪
    0.42
     seule
    0.41
    だけでなく
    0.41
     بجائے
    0.41
    Act Density 0.171%

    No Known Activations