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

    Neuronpedia

    INDEX
    Explanations

    peas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feiern
    0.94
    Commande
    0.87
    Ordenar
    0.86
    েও
    0.84
    commande
    0.82
    лната
    0.82
     редко
    0.80
    LensFlare
    0.79
     пато
    0.77
    갓
    0.77
    POSITIVE LOGITS
     amines
    1.02
     comerciales
    0.98
     fines
    0.91
     cryptocur
    0.90
    uf
    0.88
     govern
    0.86
    arán
    0.86
     cercanas
    0.86
    aj
    0.86
    overnment
    0.86
    Act Density 0.001%

    No Known Activations