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

    Neuronpedia

    INDEX
    Explanations

    location, status, or type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nagging
    0.70
     ด้วย
    0.63
    <h4>
    0.63
     degeneracy
    0.62
    <h3>
    0.60
    のだが
    0.58
     اه
    0.58
    いただく
    0.58
     Side
    0.57
    features
    0.57
    POSITIVE LOGITS
     regreso
    0.80
     計算
    0.77
    பெரும்
    0.76
     promedio
    0.75
    ွ
    0.74
     média
    0.74
    зульта
    0.74
     প্রচুর
    0.73
    lesque
    0.72
    Calcul
    0.72
    Act Density 0.000%

    No Known Activations