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

    Neuronpedia

    INDEX
    Explanations

    items and their quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lector
    0.97
     почита
    0.90
    ivational
    0.90
     Gegensatz
    0.90
    И
    0.90
     Enfin
    0.90
     Riemannian
    0.89
     Mesmo
    0.88
     hombre
    0.88
     เดียว
    0.87
    POSITIVE LOGITS
     shipments
    1.04
     vials
    1.03
     pallets
    0.98
     cartons
    0.98
     unopened
    0.97
     জব্দ
    0.96
     batches
    0.96
    奘
    0.94
     keepsake
    0.93
     सैंपल
    0.92
    Act Density 0.463%

    No Known Activations