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

    Neuronpedia

    INDEX
    Explanations

    Main St

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     città
    0.61
     miasta
    0.55
     şehr
    0.55
     teléfonos
    0.52
     telepon
    0.51
     telefon
    0.50
    市内
    0.50
     város
    0.50
    पालिका
    0.50
     mieście
    0.49
    POSITIVE LOGITS
     Production
    0.50
     Warner
    0.46
     v
    0.43
     Plant
    0.43
     Lab
    0.43
     Research
    0.42
     Set
    0.42
     Black
    0.42
     Produce
    0.42
     create
    0.42
    Act Density 0.020%

    No Known Activations