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

    Neuronpedia

    INDEX
    Explanations

    support groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     essas
    0.97
    categorie
    0.88
     comuns
    0.87
     individuais
    0.85
     absolue
    0.83
     pessoas
    0.83
     câ
    0.82
    avoro
    0.82
     persones
    0.81
     quaisquer
    0.81
    POSITIVE LOGITS
    柅
    0.83
    चय
    0.71
     Pyramid
    0.71
     biopsy
    0.71
     plabic
    0.70
    ুটি
    0.70
    ěl
    0.69
     Qur
    0.68
     اعظم
    0.68
     آد
    0.68
    Act Density 0.001%

    No Known Activations