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

    Neuronpedia

    INDEX
    Explanations

    hospitality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hábitos
    0.91
    ри
    0.82
     abhiv
    0.82
     básico
    0.81
     réalisés
    0.79
     secretos
    0.79
     vendeurs
    0.78
     límites
    0.77
     químicos
    0.76
     escritos
    0.76
    POSITIVE LOGITS
     Hospitality
    1.13
     to
    1.09
    al
    1.03
     hospitality
    1.01
    it
    1.00
    n
    0.98
    W
    0.98
    Y
    0.96
    l
    0.96
    IA
    0.94
    Act Density 0.001%

    No Known Activations